summaryrefslogtreecommitdiff
path: root/test
diff options
context:
space:
mode:
Diffstat (limited to 'test')
-rw-r--r--test/core/common/UtilsTest.cpp33
-rw-r--r--test/core/model/OntologyTest.cpp175
-rw-r--r--test/core/parser/stack/StackTest.cpp646
-rw-r--r--test/core/parser/stack/TokenRegistryTest.cpp82
-rw-r--r--test/core/parser/utils/SourceOffsetVectorTest.cpp2
-rw-r--r--test/core/parser/utils/TokenizedDataTest.cpp567
-rw-r--r--test/core/parser/utils/TokenizedDataTestUtils.hpp64
-rw-r--r--test/core/parser/utils/TokenizerTest.cpp441
-rw-r--r--test/formats/osml/OsmlStreamParserTest.cpp1208
-rw-r--r--test/formats/osxml/OsxmlEventParserTest.cpp99
10 files changed, 1975 insertions, 1342 deletions
diff --git a/test/core/common/UtilsTest.cpp b/test/core/common/UtilsTest.cpp
index 4bf1587..2aaa430 100644
--- a/test/core/common/UtilsTest.cpp
+++ b/test/core/common/UtilsTest.cpp
@@ -131,4 +131,35 @@ TEST(Utils, collapse)
ASSERT_EQ("long test", Utils::collapse(" long test "));
}
-} \ No newline at end of file
+TEST(Utils, isUserDefinedToken)
+{
+ EXPECT_FALSE(Utils::isUserDefinedToken(""));
+ EXPECT_FALSE(Utils::isUserDefinedToken("a"));
+ EXPECT_TRUE(Utils::isUserDefinedToken(":"));
+ EXPECT_TRUE(Utils::isUserDefinedToken("::"));
+ EXPECT_TRUE(Utils::isUserDefinedToken("!?"));
+ EXPECT_TRUE(Utils::isUserDefinedToken("."));
+ EXPECT_TRUE(Utils::isUserDefinedToken("<<"));
+ EXPECT_TRUE(Utils::isUserDefinedToken(">>"));
+ EXPECT_TRUE(Utils::isUserDefinedToken("''"));
+ EXPECT_TRUE(Utils::isUserDefinedToken("``"));
+ EXPECT_TRUE(Utils::isUserDefinedToken("´´"));
+ EXPECT_TRUE(Utils::isUserDefinedToken("´"));
+ EXPECT_TRUE(Utils::isUserDefinedToken("`"));
+ EXPECT_TRUE(Utils::isUserDefinedToken("<"));
+ EXPECT_TRUE(Utils::isUserDefinedToken(">"));
+ EXPECT_TRUE(Utils::isUserDefinedToken("<+>"));
+ EXPECT_FALSE(Utils::isUserDefinedToken("a:"));
+ EXPECT_FALSE(Utils::isUserDefinedToken("a:a"));
+ EXPECT_FALSE(Utils::isUserDefinedToken(":a"));
+ EXPECT_FALSE(Utils::isUserDefinedToken("{"));
+ EXPECT_FALSE(Utils::isUserDefinedToken("{{"));
+ EXPECT_FALSE(Utils::isUserDefinedToken("}}"));
+ EXPECT_FALSE(Utils::isUserDefinedToken("{{}{}"));
+ EXPECT_FALSE(Utils::isUserDefinedToken("<\\"));
+ EXPECT_FALSE(Utils::isUserDefinedToken("\\>"));
+ EXPECT_FALSE(Utils::isUserDefinedToken("{!"));
+ EXPECT_FALSE(Utils::isUserDefinedToken("< + >"));
+}
+
+}
diff --git a/test/core/model/OntologyTest.cpp b/test/core/model/OntologyTest.cpp
index 764dcb4..265e9e2 100644
--- a/test/core/model/OntologyTest.cpp
+++ b/test/core/model/OntologyTest.cpp
@@ -82,9 +82,7 @@ TEST(Ontology, testOntologyResolving)
}
// i use this wrapper due to the strange behaviour of GTEST.
-static void assertFalse(bool b){
- ASSERT_FALSE(b);
-}
+static void assertFalse(bool b) { ASSERT_FALSE(b); }
static Rooted<FieldDescriptor> createUnsortedPrimitiveField(
Handle<StructuredClass> strct, Handle<Type> type, Logger &logger, bool tree,
@@ -170,7 +168,6 @@ TEST(StructuredClass, getFieldDescriptors)
}
}
-
TEST(StructuredClass, getFieldDescriptorsCycles)
{
Logger logger;
@@ -523,6 +520,91 @@ TEST(Descriptor, getPermittedChildrenCycles)
ASSERT_EQ(A, children[0]);
}
+TEST(Descriptor, getSyntaxDescriptor)
+{
+ // build an ontology with some custom syntax.
+ Manager mgr{1};
+ Logger logger;
+ Rooted<SystemTypesystem> sys{new SystemTypesystem(mgr)};
+ // Construct the ontology
+ Rooted<Ontology> ontology{new Ontology(mgr, sys, "ontology")};
+ Rooted<StructuredClass> A{new StructuredClass(
+ mgr, "A", ontology, Cardinality::any(), {nullptr}, true, true)};
+ A->setStartToken(TokenDescriptor(Tokens::Indent));
+ A->setEndToken(TokenDescriptor(Tokens::Dedent));
+ {
+ TokenDescriptor sh{"<+>"};
+ sh.id = 1;
+ A->setShortToken(sh);
+ }
+ // check the SyntaxDescriptor
+ SyntaxDescriptor stx = A->getSyntaxDescriptor();
+ ASSERT_EQ(Tokens::Indent, stx.start);
+ ASSERT_EQ(Tokens::Dedent, stx.end);
+ ASSERT_EQ(1, stx.shortForm);
+ ASSERT_EQ(A, stx.descriptor);
+ ASSERT_TRUE(stx.isStruct());
+ ASSERT_FALSE(stx.isAnnotation());
+ ASSERT_FALSE(stx.isFieldDescriptor());
+}
+
+TEST(Descriptor, getPermittedTokens)
+{
+ // build an ontology with some custom syntax.
+ Manager mgr{1};
+ Logger logger;
+ Rooted<SystemTypesystem> sys{new SystemTypesystem(mgr)};
+ // Construct the ontology
+ Rooted<Ontology> ontology{new Ontology(mgr, sys, "ontology")};
+ // add one StructuredClass with all tokens set.
+ Rooted<StructuredClass> A{new StructuredClass(
+ mgr, "A", ontology, Cardinality::any(), {nullptr}, true, true)};
+ A->setStartToken(TokenDescriptor(Tokens::Indent));
+ A->setEndToken(TokenDescriptor(Tokens::Dedent));
+ {
+ TokenDescriptor sh{"<+>"};
+ sh.id = 1;
+ A->setShortToken(sh);
+ }
+ // add a field with one token set.
+ Rooted<FieldDescriptor> A_field = A->createFieldDescriptor(logger).first;
+ A_field->setEndToken(TokenDescriptor(Tokens::Newline));
+ A_field->addChild(A);
+ // add an annotation with start and end set.
+ Rooted<AnnotationClass> A_anno = ontology->createAnnotationClass("A");
+ {
+ TokenDescriptor start{"<"};
+ start.id = 7;
+ A_anno->setStartToken(start);
+ }
+ {
+ TokenDescriptor end{">"};
+ end.id = 8;
+ A_anno->setEndToken(end);
+ }
+ // add a trivial annotation, which should not be returned.
+ Rooted<AnnotationClass> B_anno = ontology->createAnnotationClass("B");
+ ASSERT_TRUE(ontology->validate(logger));
+
+ // check result.
+ std::vector<SyntaxDescriptor> stxs = A->getPermittedTokens();
+ ASSERT_EQ(3, stxs.size());
+ // the field should be first, because A itself should not be collected
+ // directly.
+ ASSERT_EQ(A_field, stxs[0].descriptor);
+ ASSERT_EQ(Tokens::Empty, stxs[0].start);
+ ASSERT_EQ(Tokens::Newline, stxs[0].end);
+ ASSERT_EQ(Tokens::Empty, stxs[0].shortForm);
+ ASSERT_EQ(A, stxs[1].descriptor);
+ ASSERT_EQ(Tokens::Indent, stxs[1].start);
+ ASSERT_EQ(Tokens::Dedent, stxs[1].end);
+ ASSERT_EQ(1, stxs[1].shortForm);
+ ASSERT_EQ(A_anno, stxs[2].descriptor);
+ ASSERT_EQ(7, stxs[2].start);
+ ASSERT_EQ(8, stxs[2].end);
+ ASSERT_EQ(Tokens::Empty, stxs[2].shortForm);
+}
+
TEST(StructuredClass, isSubclassOf)
{
// create an inheritance hierarchy.
@@ -619,6 +701,14 @@ TEST(Ontology, validate)
base->setName("myClass");
ASSERT_EQ(ValidationState::UNKNOWN, ontology->getValidationState());
ASSERT_TRUE(ontology->validate(logger));
+ // add an invalid short token.
+ base->setShortToken(TokenDescriptor("bla"));
+ ASSERT_EQ(ValidationState::UNKNOWN, ontology->getValidationState());
+ ASSERT_FALSE(ontology->validate(logger));
+ // make it valid.
+ base->setShortToken(TokenDescriptor("!bla!"));
+ ASSERT_EQ(ValidationState::UNKNOWN, ontology->getValidationState());
+ ASSERT_TRUE(ontology->validate(logger));
// Let's add a primitive field (without a primitive type at first)
Rooted<FieldDescriptor> base_field =
base->createPrimitiveFieldDescriptor(nullptr, logger).first;
@@ -629,6 +719,14 @@ TEST(Ontology, validate)
base_field->setPrimitiveType(sys->getStringType());
ASSERT_EQ(ValidationState::UNKNOWN, ontology->getValidationState());
ASSERT_TRUE(ontology->validate(logger));
+ // add an invalid start token.
+ base_field->setStartToken(TokenDescriptor("< + >"));
+ ASSERT_EQ(ValidationState::UNKNOWN, ontology->getValidationState());
+ ASSERT_FALSE(ontology->validate(logger));
+ // make it valid.
+ base_field->setStartToken(TokenDescriptor("<"));
+ ASSERT_EQ(ValidationState::UNKNOWN, ontology->getValidationState());
+ ASSERT_TRUE(ontology->validate(logger));
// add a subclass for our base class.
Rooted<StructuredClass> sub{new StructuredClass(mgr, "sub", ontology)};
// this should be valid in itself.
@@ -686,4 +784,71 @@ TEST(Ontology, validate)
ASSERT_TRUE(ontology->validate(logger));
}
}
-} \ No newline at end of file
+
+TEST(Ontology, getAllTokenDescriptors)
+{
+ // build an ontology with some custom syntax.
+ Manager mgr{1};
+ Logger logger;
+ Rooted<SystemTypesystem> sys{new SystemTypesystem(mgr)};
+ // Construct the ontology
+ Rooted<Ontology> ontology{new Ontology(mgr, sys, "ontology")};
+ // add one StructuredClass with all tokens set.
+ Rooted<StructuredClass> A{new StructuredClass(
+ mgr, "A", ontology, Cardinality::any(), {nullptr}, true, true)};
+ A->setStartToken(TokenDescriptor(Tokens::Indent));
+ A->setEndToken(TokenDescriptor(Tokens::Dedent));
+ {
+ TokenDescriptor sh{"<+>"};
+ sh.id = 1;
+ A->setShortToken(sh);
+ }
+ // add a field with one token set.
+ Rooted<FieldDescriptor> A_field = A->createFieldDescriptor(logger).first;
+ A_field->setEndToken(TokenDescriptor(Tokens::Newline));
+ A_field->addChild(A);
+ // add an annotation with start and end set.
+ Rooted<AnnotationClass> A_anno = ontology->createAnnotationClass("A");
+ {
+ TokenDescriptor start{"<"};
+ start.id = 7;
+ A_anno->setStartToken(start);
+ }
+ {
+ TokenDescriptor end{">"};
+ end.id = 8;
+ A_anno->setEndToken(end);
+ }
+ // add a trivial annotation, which should not be returned.
+ Rooted<AnnotationClass> B_anno = ontology->createAnnotationClass("B");
+ ASSERT_TRUE(ontology->validate(logger));
+
+ // check the result.
+ std::vector<TokenDescriptor *> tks = ontology->getAllTokenDescriptors();
+
+ // A short token
+ ASSERT_EQ("<+>", tks[0]->token);
+ ASSERT_EQ(1, tks[0]->id);
+ ASSERT_FALSE(tks[0]->special);
+ // A start token
+ ASSERT_EQ("", tks[1]->token);
+ ASSERT_EQ(Tokens::Indent, tks[1]->id);
+ ASSERT_TRUE(tks[1]->special);
+ // A end token
+ ASSERT_EQ("", tks[2]->token);
+ ASSERT_EQ(Tokens::Dedent, tks[2]->id);
+ ASSERT_TRUE(tks[2]->special);
+ // A field end token
+ ASSERT_EQ("", tks[3]->token);
+ ASSERT_EQ(Tokens::Newline, tks[3]->id);
+ ASSERT_TRUE(tks[3]->special);
+ // A anno start token
+ ASSERT_EQ("<", tks[4]->token);
+ ASSERT_EQ(7, tks[4]->id);
+ ASSERT_FALSE(tks[4]->special);
+ // A anno end token
+ ASSERT_EQ(">", tks[5]->token);
+ ASSERT_EQ(8, tks[5]->id);
+ ASSERT_FALSE(tks[5]->special);
+}
+}
diff --git a/test/core/parser/stack/StackTest.cpp b/test/core/parser/stack/StackTest.cpp
index a93f14a..a831c32 100644
--- a/test/core/parser/stack/StackTest.cpp
+++ b/test/core/parser/stack/StackTest.cpp
@@ -21,9 +21,11 @@
#include <gtest/gtest.h>
#include <core/frontend/TerminalLogger.hpp>
+#include <core/parser/stack/Callbacks.hpp>
#include <core/parser/stack/Handler.hpp>
#include <core/parser/stack/Stack.hpp>
#include <core/parser/stack/State.hpp>
+#include <core/parser/utils/TokenizedData.hpp>
#include <core/StandaloneEnvironment.hpp>
@@ -37,70 +39,88 @@ static StandaloneEnvironment env(logger);
namespace {
+class Parser : public ParserCallbacks {
+ TokenId registerToken(const std::string &token) override
+ {
+ return Tokens::Empty;
+ }
+
+ void unregisterToken(TokenId id) override
+ {
+ // Do nothing here
+ }
+};
+
+static Parser parser;
+
struct Tracker {
- int startCount;
+ int startCommandCount;
+ int startAnnotationCount;
+ int startTokenCount;
+ int endTokenCount;
int endCount;
int fieldStartCount;
int fieldEndCount;
- int annotationStartCount;
- int annotationEndCount;
int dataCount;
- Variant::mapType startArgs;
- bool fieldStartIsDefault;
- size_t fieldStartIdx;
- Variant annotationStartClassName;
- Variant::mapType annotationStartArgs;
- Variant annotationEndClassName;
- Variant annotationEndElementName;
- Variant dataData;
-
- bool startResult;
- bool fieldStartSetIsDefault;
+ bool startCommandResult;
+ bool startAnnotationResult;
+ bool startTokenResult;
+ Handler::EndTokenResult endTokenResult;
bool fieldStartResult;
- bool annotationStartResult;
- bool annotationEndResult;
bool dataResult;
+ Variant::mapType startCommandArgs;
+ Variant::mapType startAnnotationArgs;
+
+ bool fieldStartReturnValue;
+ size_t fieldStartIdx;
+ bool fieldStartIsDefault;
+ bool fieldStartSetIsDefault;
+
+ Variant dataData;
+
Tracker() { reset(); }
void reset()
{
- startCount = 0;
+ startCommandCount = 0;
+ startAnnotationCount = 0;
+ startTokenCount = 0;
+ endTokenCount = 0;
endCount = 0;
fieldStartCount = 0;
fieldEndCount = 0;
- annotationStartCount = 0;
- annotationEndCount = 0;
dataCount = 0;
- startArgs = Variant::mapType{};
- fieldStartIsDefault = false;
- fieldStartIdx = 0;
- annotationStartClassName = Variant::fromString(std::string{});
- annotationStartArgs = Variant::mapType{};
- annotationEndClassName = Variant::fromString(std::string{});
- annotationEndElementName = Variant::fromString(std::string{});
- dataData = Variant::fromString(std::string{});
-
- startResult = true;
- fieldStartSetIsDefault = false;
+ startCommandResult = true;
+ startAnnotationResult = true;
+ startTokenResult = true;
+ endTokenResult = Handler::EndTokenResult::ENDED_THIS;
fieldStartResult = true;
- annotationStartResult = true;
- annotationEndResult = true;
dataResult = true;
+
+ startCommandArgs = Variant::mapType{};
+ startAnnotationArgs = Variant::mapType{};
+
+ fieldStartIdx = 0;
+ fieldStartIsDefault = false;
+ fieldStartSetIsDefault = false;
+
+ dataData = Variant{};
}
- void expect(int startCount, int endCount, int fieldStartCount,
- int fieldEndCount, int annotationStartCount,
- int annotationEndCount, int dataCount)
+ void expect(int startCommandCount, int endCount, int fieldStartCount,
+ int fieldEndCount, int dataCount, int startAnnotationCount = 0,
+ int startTokenCount = 0, int endTokenCount = 0)
{
- EXPECT_EQ(startCount, this->startCount);
+ EXPECT_EQ(startCommandCount, this->startCommandCount);
+ EXPECT_EQ(startAnnotationCount, this->startAnnotationCount);
+ EXPECT_EQ(startTokenCount, this->startTokenCount);
+ EXPECT_EQ(endTokenCount, this->endTokenCount);
EXPECT_EQ(endCount, this->endCount);
EXPECT_EQ(fieldStartCount, this->fieldStartCount);
EXPECT_EQ(fieldEndCount, this->fieldEndCount);
- EXPECT_EQ(annotationStartCount, this->annotationStartCount);
- EXPECT_EQ(annotationEndCount, this->annotationEndCount);
EXPECT_EQ(dataCount, this->dataCount);
}
};
@@ -112,55 +132,57 @@ private:
TestHandler(const HandlerData &handlerData) : Handler(handlerData) {}
public:
- bool start(Variant::mapType &args) override
+ bool startCommand(Variant::mapType &args) override
{
- tracker.startCount++;
- tracker.startArgs = args;
- if (!tracker.startResult) {
+ tracker.startCommandArgs = args;
+ tracker.startCommandCount++;
+ if (!tracker.startCommandResult) {
logger().error(
- "The TestHandler was told not to allow a field start. So it "
- "doesn't. The TestHandler always obeys its master.");
+ "TestHandler was told not to allow a command start. "
+ "TestHandler always obeys its master.");
}
- return tracker.startResult;
+ return tracker.startCommandResult;
+ }
+
+ bool startAnnotation(Variant::mapType &args,
+ AnnotationType annotationType) override
+ {
+ tracker.startAnnotationArgs = args;
+ tracker.startAnnotationCount++;
+ return tracker.startAnnotationResult;
+ }
+
+ bool startToken(Handle<Node> node) override
+ {
+ tracker.startTokenCount++;
+ return tracker.startTokenResult;
+ }
+
+ EndTokenResult endToken(const Token &token, Handle<Node> node) override
+ {
+ tracker.endTokenCount++;
+ return tracker.endTokenResult;
}
void end() override { tracker.endCount++; }
bool fieldStart(bool &isDefault, size_t fieldIdx) override
{
- tracker.fieldStartCount++;
tracker.fieldStartIsDefault = isDefault;
tracker.fieldStartIdx = fieldIdx;
if (tracker.fieldStartSetIsDefault) {
isDefault = true;
}
+ tracker.fieldStartCount++;
return tracker.fieldStartResult;
}
void fieldEnd() override { tracker.fieldEndCount++; }
- bool annotationStart(const Variant &className,
- Variant::mapType &args) override
- {
- tracker.annotationStartCount++;
- tracker.annotationStartClassName = className;
- tracker.annotationStartArgs = args;
- return tracker.annotationStartResult;
- }
-
- bool annotationEnd(const Variant &className,
- const Variant &elementName) override
- {
- tracker.annotationEndCount++;
- tracker.annotationEndClassName = className;
- tracker.annotationEndElementName = elementName;
- return tracker.annotationEndResult;
- }
-
- bool data(Variant &data) override
+ bool data() override
{
+ tracker.dataData = readData();
tracker.dataCount++;
- tracker.dataData = data;
return tracker.dataResult;
}
@@ -204,75 +226,137 @@ TEST(Stack, basicTest)
tracker.reset();
logger.reset();
{
- Stack s{env.context, States::TestHandlers};
+ Stack s{parser, env.context, States::TestHandlers};
EXPECT_EQ("", s.currentCommandName());
EXPECT_EQ(&States::None, &s.currentState());
- s.command("document", {});
+ s.commandStart("document", {});
s.fieldStart(true);
s.data("test1");
EXPECT_EQ("document", s.currentCommandName());
EXPECT_EQ(&States::Document, &s.currentState());
- tracker.expect(1, 0, 1, 0, 0, 0, 1); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 1, 0, 1); // scc, ec, fsc, fec, dc, sac, stc, etc
- s.command("body", {});
+ s.commandStart("body", {});
s.fieldStart(true);
s.data("test2");
EXPECT_EQ("body", s.currentCommandName());
EXPECT_EQ(&States::Body, &s.currentState());
- tracker.expect(2, 0, 2, 0, 0, 0, 2); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(2, 0, 2, 0, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
- s.command("inner", {});
+ s.commandStart("inner", {});
s.fieldStart(true);
EXPECT_EQ("inner", s.currentCommandName());
EXPECT_EQ(&States::BodyChildren, &s.currentState());
s.fieldEnd();
- tracker.expect(3, 0, 3, 1, 0, 0, 2); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(3, 0, 3, 1, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
s.fieldEnd();
EXPECT_EQ("body", s.currentCommandName());
EXPECT_EQ(&States::Body, &s.currentState());
- tracker.expect(3, 1, 3, 2, 0, 0, 2); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(3, 1, 3, 2, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
- s.command("body", {});
+ s.commandStart("body", {});
EXPECT_EQ("body", s.currentCommandName());
EXPECT_EQ(&States::Body, &s.currentState());
- tracker.expect(4, 2, 3, 2, 0, 0, 2); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(4, 2, 3, 2, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
s.fieldStart(true);
s.data("test3");
EXPECT_EQ("body", s.currentCommandName());
EXPECT_EQ(&States::Body, &s.currentState());
s.fieldEnd();
- tracker.expect(4, 2, 4, 3, 0, 0, 3); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(4, 2, 4, 3, 3); // scc, ec, fsc, fec, dc, sac, stc, etc
EXPECT_EQ("body", s.currentCommandName());
EXPECT_EQ(&States::Body, &s.currentState());
s.fieldEnd();
- tracker.expect(4, 3, 4, 4, 0, 0, 3); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(4, 3, 4, 4, 3); // scc, ec, fsc, fec, dc, sac, stc, etc
EXPECT_EQ("document", s.currentCommandName());
EXPECT_EQ(&States::Document, &s.currentState());
}
- tracker.expect(4, 4, 4, 4, 0, 0, 3); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(4, 4, 4, 4, 3); // scc, ec, fsc, fec, dc, sac, stc, etc
+ ASSERT_FALSE(logger.hasError());
+}
+
+TEST(Stack, basicTestRangeCommands)
+{
+ tracker.reset();
+ logger.reset();
+ {
+ Stack s{parser, env.context, States::TestHandlers};
+
+ EXPECT_EQ("", s.currentCommandName());
+ EXPECT_EQ(&States::None, &s.currentState());
+
+ s.commandStart("document", {}, true);
+ EXPECT_EQ("document", s.currentCommandName());
+ EXPECT_EQ(&States::Document, &s.currentState());
+ tracker.expect(1, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
+
+ s.data("test1");
+ tracker.expect(1, 0, 1, 0, 1); // scc, ec, fsc, fec, dc, sac, stc, etc
+
+ s.commandStart("body", {}, true);
+ tracker.expect(2, 0, 1, 0, 1); // scc, ec, fsc, fec, dc, sac, stc, etc
+ s.data("test2");
+ tracker.expect(2, 0, 2, 0, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
+ EXPECT_EQ("body", s.currentCommandName());
+ EXPECT_EQ(&States::Body, &s.currentState());
+
+ s.commandStart("inner", {}, true);
+ tracker.expect(3, 0, 2, 0, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
+ EXPECT_EQ("inner", s.currentCommandName());
+ EXPECT_EQ(&States::BodyChildren, &s.currentState());
+ s.rangeEnd();
+ tracker.expect(3, 1, 3, 1, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
+ EXPECT_EQ("body", s.currentCommandName());
+ EXPECT_EQ(&States::Body, &s.currentState());
+ s.rangeEnd();
+ tracker.expect(3, 2, 3, 2, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
+
+ s.commandStart("body", {}, true);
+ EXPECT_EQ("body", s.currentCommandName());
+ EXPECT_EQ(&States::Body, &s.currentState());
+ tracker.expect(4, 2, 3, 2, 2); // scc, ec, fsc, fse, dc, sac, stc, etc
+ s.fieldStart(true);
+ tracker.expect(4, 2, 4, 2, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
+ s.data("test3");
+ tracker.expect(4, 2, 4, 2, 3); // scc, ec, fsc, fec, dc, sac, stc, etc
+ EXPECT_EQ("body", s.currentCommandName());
+ EXPECT_EQ(&States::Body, &s.currentState());
+ s.fieldEnd();
+ tracker.expect(4, 2, 4, 3, 3); // scc, ec, fsc, fec, dc, sac, stc, etc
+ EXPECT_EQ("body", s.currentCommandName());
+ EXPECT_EQ(&States::Body, &s.currentState());
+ s.rangeEnd();
+ tracker.expect(4, 3, 4, 3, 3); // scc, ec, fsc, fec, dc, sac, stc, etc
+
+ EXPECT_EQ("document", s.currentCommandName());
+ EXPECT_EQ(&States::Document, &s.currentState());
+ s.rangeEnd();
+ tracker.expect(4, 4, 4, 4, 3); // scc, ec, fsc, fec, dc, sac, stc, etc
+ }
+ tracker.expect(4, 4, 4, 4, 3); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_FALSE(logger.hasError());
}
TEST(Stack, errorInvalidCommands)
{
- Stack s{env.context, States::TestHandlers};
+ Stack s{parser, env.context, States::TestHandlers};
tracker.reset();
- EXPECT_THROW(s.command("body", {}), LoggableException);
- s.command("document", {});
+ EXPECT_THROW(s.commandStart("body", {}), LoggableException);
+ s.commandStart("document", {});
s.fieldStart(true);
- EXPECT_THROW(s.command("document", {}), LoggableException);
- s.command("empty", {});
+ EXPECT_THROW(s.commandStart("document", {}), LoggableException);
+ s.commandStart("empty", {});
s.fieldStart(true);
- EXPECT_THROW(s.command("body", {}), LoggableException);
- s.command("special", {});
+ EXPECT_THROW(s.commandStart("body", {}), LoggableException);
+ s.commandStart("special", {});
s.fieldStart(true);
s.fieldEnd();
s.fieldEnd();
@@ -288,23 +372,23 @@ TEST(Stack, errorInvalidCommands)
TEST(Stack, validation)
{
- Stack s{env.context, States::TestHandlers};
+ Stack s{parser, env.context, States::TestHandlers};
tracker.reset();
logger.reset();
- s.command("arguments", {});
+ s.commandStart("arguments", {});
EXPECT_TRUE(logger.hasError());
s.fieldStart(true);
s.fieldEnd();
logger.reset();
- s.command("arguments", {{"a", 5}});
+ s.commandStart("arguments", {{"a", 5}}, false);
EXPECT_TRUE(logger.hasError());
s.fieldStart(true);
s.fieldEnd();
logger.reset();
- s.command("arguments", {{"a", 5}, {"b", "test"}});
+ s.commandStart("arguments", {{"a", 5}, {"b", "test"}}, false);
EXPECT_FALSE(logger.hasError());
s.fieldStart(true);
s.fieldEnd();
@@ -315,33 +399,33 @@ TEST(Stack, invalidCommandName)
tracker.reset();
logger.reset();
- Stack s{env.context, States::AnyHandlers};
- s.command("a", {});
- tracker.expect(1, 0, 0, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ Stack s{parser, env.context, States::AnyHandlers};
+ s.commandStart("a", {});
+ tracker.expect(1, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
s.fieldStart(true);
s.fieldEnd();
- tracker.expect(1, 0, 1, 1, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 1, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
- s.command("a_", {});
- tracker.expect(2, 1, 1, 1, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ s.commandStart("a_", {});
+ tracker.expect(2, 1, 1, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
s.fieldStart(true);
s.fieldEnd();
- tracker.expect(2, 1, 2, 2, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(2, 1, 2, 2, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
- s.command("a_:b", {});
- tracker.expect(3, 2, 2, 2, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ s.commandStart("a_:b", {});
+ tracker.expect(3, 2, 2, 2, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
s.fieldStart(true);
s.fieldEnd();
- tracker.expect(3, 2, 3, 3, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(3, 2, 3, 3, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
- ASSERT_THROW(s.command("_a", {}), LoggableException);
- tracker.expect(3, 3, 3, 3, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ ASSERT_THROW(s.commandStart("_a", {}), LoggableException);
+ tracker.expect(3, 3, 3, 3, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
- ASSERT_THROW(s.command("a:", {}), LoggableException);
- tracker.expect(3, 3, 3, 3, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ ASSERT_THROW(s.commandStart("a:", {}), LoggableException);
+ tracker.expect(3, 3, 3, 3, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
- ASSERT_THROW(s.command("a:_b", {}), LoggableException);
- tracker.expect(3, 3, 3, 3, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ ASSERT_THROW(s.commandStart("a:_b", {}), LoggableException);
+ tracker.expect(3, 3, 3, 3, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
}
TEST(Stack, multipleFields)
@@ -349,50 +433,50 @@ TEST(Stack, multipleFields)
tracker.reset();
logger.reset();
{
- Stack s{env.context, States::AnyHandlers};
+ Stack s{parser, env.context, States::AnyHandlers};
- s.command("a", {{"a", false}});
- tracker.expect(1, 0, 0, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ s.commandStart("a", {{"a", false}}, false);
+ tracker.expect(1, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
EXPECT_EQ("a", s.currentCommandName());
- EXPECT_EQ(Variant::mapType({{"a", false}}), tracker.startArgs);
+ EXPECT_EQ(Variant::mapType({{"a", false}}), tracker.startCommandArgs);
s.fieldStart(false);
- tracker.expect(1, 0, 1, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 1, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
EXPECT_FALSE(tracker.fieldStartIsDefault);
EXPECT_EQ(0U, tracker.fieldStartIdx);
s.data("test");
- tracker.expect(1, 0, 1, 0, 0, 0, 1); // sc, ec, fsc, fse, asc, aec, dc
- EXPECT_EQ("test", tracker.dataData);
+ tracker.expect(1, 0, 1, 0, 1); // scc, ec, fsc, fec, dc, sac, stc, etc
+ EXPECT_EQ("test", tracker.dataData.asString());
s.fieldEnd();
- tracker.expect(1, 0, 1, 1, 0, 0, 1); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 1, 1, 1); // scc, ec, fsc, fec, dc, sac, stc, etc
s.fieldStart(false);
- tracker.expect(1, 0, 2, 1, 0, 0, 1); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 2, 1, 1); // scc, ec, fsc, fec, dc, sac, stc, etc
EXPECT_FALSE(tracker.fieldStartIsDefault);
EXPECT_EQ(1U, tracker.fieldStartIdx);
s.data("test2");
- tracker.expect(1, 0, 2, 1, 0, 0, 2); // sc, ec, fsc, fse, asc, aec, dc
- EXPECT_EQ("test2", tracker.dataData);
+ tracker.expect(1, 0, 2, 1, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
+ EXPECT_EQ("test2", tracker.dataData.asString());
s.fieldEnd();
- tracker.expect(1, 0, 2, 2, 0, 0, 2); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 2, 2, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
s.fieldStart(true);
- tracker.expect(1, 0, 3, 2, 0, 0, 2); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 3, 2, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
EXPECT_TRUE(tracker.fieldStartIsDefault);
EXPECT_EQ(2U, tracker.fieldStartIdx);
s.data("test3");
- tracker.expect(1, 0, 3, 2, 0, 0, 3); // sc, ec, fsc, fse, asc, aec, dc
- EXPECT_EQ("test3", tracker.dataData);
+ tracker.expect(1, 0, 3, 2, 3); // scc, ec, fsc, fec, dc, sac, stc, etc
+ EXPECT_EQ("test3", tracker.dataData.asString());
s.fieldEnd();
- tracker.expect(1, 0, 3, 3, 0, 0, 3); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 3, 3, 3); // scc, ec, fsc, fec, dc, sac, stc, etc
}
- tracker.expect(1, 1, 3, 3, 0, 0, 3); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 1, 3, 3, 3); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_FALSE(logger.hasError());
}
@@ -401,15 +485,15 @@ TEST(Stack, implicitDefaultFieldOnNewCommand)
tracker.reset();
logger.reset();
{
- Stack s{env.context, States::AnyHandlers};
+ Stack s{parser, env.context, States::AnyHandlers};
- s.command("a", {});
- tracker.expect(1, 0, 0, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ s.commandStart("a", {});
+ tracker.expect(1, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
- s.command("b", {});
- tracker.expect(2, 0, 1, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ s.commandStart("b", {});
+ tracker.expect(2, 0, 1, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
}
- tracker.expect(2, 2, 1, 1, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(2, 2, 1, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_FALSE(logger.hasError());
}
@@ -418,21 +502,21 @@ TEST(Stack, implicitDefaultFieldOnNewCommandWithExplicitDefaultField)
tracker.reset();
logger.reset();
{
- Stack s{env.context, States::AnyHandlers};
+ Stack s{parser, env.context, States::AnyHandlers};
- s.command("a", {});
- tracker.expect(1, 0, 0, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ s.commandStart("a", {});
+ tracker.expect(1, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_EQ("a", s.currentCommandName());
- s.command("b", {});
- tracker.expect(2, 0, 1, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ s.commandStart("b", {});
+ tracker.expect(2, 0, 1, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_EQ("b", s.currentCommandName());
s.fieldStart(true);
s.fieldEnd();
- tracker.expect(2, 0, 2, 1, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(2, 0, 2, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_EQ("b", s.currentCommandName());
}
- tracker.expect(2, 2, 2, 2, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(2, 2, 2, 2, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_FALSE(logger.hasError());
}
@@ -441,18 +525,18 @@ TEST(Stack, noImplicitDefaultFieldOnIncompatibleCommand)
tracker.reset();
logger.reset();
{
- Stack s{env.context, States::AnyHandlers};
+ Stack s{parser, env.context, States::AnyHandlers};
- s.command("a", {});
- tracker.expect(1, 0, 0, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ s.commandStart("a", {});
+ tracker.expect(1, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_EQ("a", s.currentCommandName());
tracker.fieldStartResult = false;
- s.command("b", {});
- tracker.expect(2, 1, 1, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ s.commandStart("b", {});
+ tracker.expect(2, 1, 1, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_EQ("b", s.currentCommandName());
}
- tracker.expect(2, 2, 1, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(2, 2, 1, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_FALSE(logger.hasError());
}
@@ -461,23 +545,23 @@ TEST(Stack, noImplicitDefaultFieldIfDefaultFieldGiven)
tracker.reset();
logger.reset();
{
- Stack s{env.context, States::AnyHandlers};
+ Stack s{parser, env.context, States::AnyHandlers};
- s.command("a", {});
- tracker.expect(1, 0, 0, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ s.commandStart("a", {});
+ tracker.expect(1, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_EQ("a", s.currentCommandName());
s.fieldStart(true);
- tracker.expect(1, 0, 1, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 1, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_EQ("a", s.currentCommandName());
s.fieldEnd();
- tracker.expect(1, 0, 1, 1, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 1, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_EQ("a", s.currentCommandName());
- s.command("b", {});
- tracker.expect(2, 1, 1, 1, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ s.commandStart("b", {});
+ tracker.expect(2, 1, 1, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_EQ("b", s.currentCommandName());
}
- tracker.expect(2, 2, 1, 1, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(2, 2, 1, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_FALSE(logger.hasError());
}
@@ -486,18 +570,18 @@ TEST(Stack, noEndIfStartFails)
tracker.reset();
logger.reset();
{
- Stack s{env.context, States::AnyHandlers};
+ Stack s{parser, env.context, States::AnyHandlers};
- s.command("a", {});
- tracker.expect(1, 0, 0, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ s.commandStart("a", {});
+ tracker.expect(1, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_EQ("a", s.currentCommandName());
- tracker.startResult = false;
- s.command("b", {});
- tracker.expect(3, 1, 1, 1, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
- ASSERT_EQ("b", s.currentCommandName());
+ tracker.startCommandResult = false;
+ s.commandStart("b", {});
+ tracker.expect(3, 1, 1, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
+ EXPECT_EQ(&States::None, &s.currentState());
}
- tracker.expect(3, 1, 1, 1, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(3, 1, 1, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_TRUE(logger.hasError());
}
@@ -506,15 +590,15 @@ TEST(Stack, implicitDefaultFieldOnData)
tracker.reset();
logger.reset();
{
- Stack s{env.context, States::AnyHandlers};
+ Stack s{parser, env.context, States::AnyHandlers};
- s.command("a", {});
- tracker.expect(1, 0, 0, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ s.commandStart("a", {});
+ tracker.expect(1, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
s.data("test");
- tracker.expect(1, 0, 1, 0, 0, 0, 1); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 1, 0, 1); // scc, ec, fsc, fec, dc, sac, stc, etc
}
- tracker.expect(1, 1, 1, 1, 0, 0, 1); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 1, 1, 1, 1); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_FALSE(logger.hasError());
}
@@ -524,11 +608,11 @@ TEST(Stack, autoFieldEnd)
logger.reset();
{
- Stack s{env.context, States::AnyHandlers};
- s.command("a", {});
- tracker.expect(1, 0, 0, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ Stack s{parser, env.context, States::AnyHandlers};
+ s.commandStart("a", {});
+ tracker.expect(1, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
}
- tracker.expect(1, 1, 0, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 1, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_FALSE(logger.hasError());
}
@@ -538,17 +622,17 @@ TEST(Stack, autoImplicitFieldEnd)
logger.reset();
{
- Stack s{env.context, States::AnyHandlers};
- s.command("a", {});
- s.command("b", {});
- s.command("c", {});
- s.command("d", {});
- s.command("e", {});
+ Stack s{parser, env.context, States::AnyHandlers};
+ s.commandStart("a", {});
+ s.commandStart("b", {});
+ s.commandStart("c", {});
+ s.commandStart("d", {});
+ s.commandStart("e", {});
s.fieldStart(true);
s.fieldEnd();
- tracker.expect(5, 0, 5, 1, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(5, 0, 5, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
}
- tracker.expect(5, 5, 5, 5, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(5, 5, 5, 5, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_FALSE(logger.hasError());
}
@@ -558,14 +642,14 @@ TEST(Stack, invalidDefaultField)
logger.reset();
{
- Stack s{env.context, States::AnyHandlers};
- s.command("a", {});
+ Stack s{parser, env.context, States::AnyHandlers};
+ s.commandStart("a", {});
tracker.fieldStartResult = false;
s.fieldStart(true);
s.fieldEnd();
- tracker.expect(1, 0, 1, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 1, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
}
- tracker.expect(1, 1, 1, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 1, 1, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
ASSERT_FALSE(logger.hasError());
}
@@ -575,17 +659,17 @@ TEST(Stack, errorInvalidDefaultFieldData)
logger.reset();
{
- Stack s{env.context, States::AnyHandlers};
- s.command("a", {});
+ Stack s{parser, env.context, States::AnyHandlers};
+ s.commandStart("a", {});
tracker.fieldStartResult = false;
s.fieldStart(true);
ASSERT_FALSE(logger.hasError());
s.data("test");
ASSERT_TRUE(logger.hasError());
s.fieldEnd();
- tracker.expect(1, 0, 1, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 1, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
}
- tracker.expect(1, 1, 1, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 1, 1, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
}
TEST(Stack, errorInvalidFieldData)
@@ -594,17 +678,17 @@ TEST(Stack, errorInvalidFieldData)
logger.reset();
{
- Stack s{env.context, States::AnyHandlers};
- s.command("a", {});
+ Stack s{parser, env.context, States::AnyHandlers};
+ s.commandStart("a", {});
tracker.fieldStartResult = false;
ASSERT_FALSE(logger.hasError());
s.fieldStart(false);
ASSERT_TRUE(logger.hasError());
s.data("test");
s.fieldEnd();
- tracker.expect(1, 0, 1, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 1, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
}
- tracker.expect(1, 1, 1, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 1, 1, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
}
TEST(Stack, errorFieldStartNoCommand)
@@ -612,10 +696,10 @@ TEST(Stack, errorFieldStartNoCommand)
tracker.reset();
logger.reset();
- Stack s{env.context, States::AnyHandlers};
+ Stack s{parser, env.context, States::AnyHandlers};
ASSERT_THROW(s.fieldStart(false), LoggableException);
ASSERT_THROW(s.fieldStart(true), LoggableException);
- tracker.expect(0, 0, 0, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(0, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
}
TEST(Stack, errorMultipleFieldStarts)
@@ -624,20 +708,20 @@ TEST(Stack, errorMultipleFieldStarts)
logger.reset();
{
- Stack s{env.context, States::AnyHandlers};
- s.command("a", {});
- tracker.expect(1, 0, 0, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ Stack s{parser, env.context, States::AnyHandlers};
+ s.commandStart("a", {});
+ tracker.expect(1, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
s.fieldStart(false);
ASSERT_FALSE(logger.hasError());
s.fieldStart(false);
ASSERT_TRUE(logger.hasError());
- tracker.expect(1, 0, 1, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 1, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
s.fieldEnd();
- tracker.expect(1, 0, 1, 1, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 1, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
}
- tracker.expect(1, 1, 1, 1, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 1, 1, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
}
TEST(Stack, errorMultipleFieldEnds)
@@ -646,102 +730,122 @@ TEST(Stack, errorMultipleFieldEnds)
logger.reset();
{
- Stack s{env.context, States::AnyHandlers};
- s.command("a", {});
- tracker.expect(1, 0, 0, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ Stack s{parser, env.context, States::AnyHandlers};
+ s.commandStart("a", {});
+ tracker.expect(1, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
s.fieldStart(false);
s.fieldEnd();
ASSERT_FALSE(logger.hasError());
- tracker.expect(1, 0, 1, 1, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 0, 1, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
s.fieldEnd();
ASSERT_TRUE(logger.hasError());
- tracker.expect(1, 1, 1, 1, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 1, 1, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
}
- tracker.expect(1, 1, 1, 1, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.expect(1, 1, 1, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
}
TEST(Stack, errorOpenField)
{
- tracker.reset();
- logger.reset();
-
- {
- Stack s{env.context, States::AnyHandlers};
- s.command("a", {});
- tracker.expect(1, 0, 0, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
-
- s.fieldStart(false);
- ASSERT_FALSE(logger.hasError());
- }
- ASSERT_TRUE(logger.hasError());
- tracker.expect(1, 1, 1, 1, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.reset();
+ logger.reset();
+
+ {
+ Stack s{parser, env.context, States::AnyHandlers};
+ s.commandStart("a", {});
+ tracker.expect(1, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
+
+ s.fieldStart(false);
+ ASSERT_FALSE(logger.hasError());
+ }
+ ASSERT_TRUE(logger.hasError());
+ tracker.expect(1, 1, 1, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
}
TEST(Stack, fieldEndWhenImplicitDefaultFieldOpen)
{
- tracker.reset();
- logger.reset();
-
- {
- Stack s{env.context, States::AnyHandlers};
- s.command("a", {});
- s.fieldStart(true);
- s.command("b", {});
- s.data("test");
- s.fieldEnd();
- tracker.expect(2, 1, 2, 2, 0, 0, 1); // sc, ec, fsc, fse, asc, aec, dc
- }
- tracker.expect(2, 2, 2, 2, 0, 0, 1); // sc, ec, fsc, fse, asc, aec, dc
- ASSERT_FALSE(logger.hasError());
+ tracker.reset();
+ logger.reset();
+
+ {
+ Stack s{parser, env.context, States::AnyHandlers};
+ s.commandStart("a", {});
+ s.fieldStart(true);
+ s.commandStart("b", {});
+ s.data("test");
+ s.fieldEnd();
+ tracker.expect(2, 1, 2, 2, 1); // scc, ec, fsc, fec, dc, sac, stc, etc
+ }
+ tracker.expect(2, 2, 2, 2, 1); // scc, ec, fsc, fec, dc, sac, stc, etc
+ ASSERT_FALSE(logger.hasError());
}
TEST(Stack, fieldAfterDefaultField)
{
- tracker.reset();
- logger.reset();
-
- {
- Stack s{env.context, States::AnyHandlers};
- s.command("a", {});
- tracker.expect(1, 0, 0, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
- s.fieldStart(true);
- tracker.expect(1, 0, 1, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
-
- s.command("b", {});
- tracker.expect(2, 0, 1, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
-
- s.fieldStart(false);
- tracker.expect(2, 0, 2, 0, 0, 0, 0); // sc, ec, fsc, fse, asc, aec, dc
- s.data("f1");
- tracker.expect(2, 0, 2, 0, 0, 0, 1); // sc, ec, fsc, fse, asc, aec, dc
- s.fieldEnd();
- tracker.expect(2, 0, 2, 1, 0, 0, 1); // sc, ec, fsc, fse, asc, aec, dc
- tracker.fieldStartSetIsDefault = true;
-
- s.fieldStart(false);
- tracker.fieldStartSetIsDefault = false;
- tracker.expect(2, 0, 3, 1, 0, 0, 1); // sc, ec, fsc, fse, asc, aec, dc
- s.data("f2");
- tracker.expect(2, 0, 3, 1, 0, 0, 2); // sc, ec, fsc, fse, asc, aec, dc
- s.fieldEnd();
- tracker.expect(2, 0, 3, 2, 0, 0, 2); // sc, ec, fsc, fse, asc, aec, dc
+ tracker.reset();
+ logger.reset();
+
+ {
+ Stack s{parser, env.context, States::AnyHandlers};
+ s.commandStart("a", {});
+ tracker.expect(1, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
+ s.fieldStart(true);
+ tracker.expect(1, 0, 1, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
+
+ s.commandStart("b", {});
+ tracker.expect(2, 0, 1, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
+
+ s.fieldStart(false);
+ tracker.expect(2, 0, 2, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
+ s.data("f1");
+ tracker.expect(2, 0, 2, 0, 1); // scc, ec, fsc, fec, dc, sac, stc, etc
+ s.fieldEnd();
+ tracker.expect(2, 0, 2, 1, 1); // scc, ec, fsc, fec, dc, sac, stc, etc
+ tracker.fieldStartSetIsDefault = true;
+
+ s.fieldStart(false);
+ tracker.fieldStartSetIsDefault = false;
+ tracker.expect(2, 0, 3, 1, 1); // scc, ec, fsc, fec, dc, sac, stc, etc
+ s.data("f2");
+ tracker.expect(2, 0, 3, 1, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
+ s.fieldEnd();
+ tracker.expect(2, 0, 3, 2, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
+
+ ASSERT_FALSE(logger.hasError());
+ s.fieldStart(false);
+ ASSERT_TRUE(logger.hasError());
+ logger.reset();
+ tracker.expect(2, 0, 3, 2, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
+ s.data("f3");
+ tracker.expect(2, 0, 3, 2, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
+ s.fieldEnd();
+ tracker.expect(2, 0, 3, 2, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
+
+ s.fieldEnd();
+ tracker.expect(2, 1, 3, 3, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
+ }
+ tracker.expect(2, 2, 3, 3, 2); // scc, ec, fsc, fec, dc, sac, stc, etc
+ ASSERT_FALSE(logger.hasError());
+}
- ASSERT_FALSE(logger.hasError());
- s.fieldStart(false);
- ASSERT_TRUE(logger.hasError());
- logger.reset();
- tracker.expect(2, 0, 3, 2, 0, 0, 2); // sc, ec, fsc, fse, asc, aec, dc
- s.data("f3");
- tracker.expect(2, 0, 3, 2, 0, 0, 2); // sc, ec, fsc, fse, asc, aec, dc
- s.fieldEnd();
- tracker.expect(2, 0, 3, 2, 0, 0, 2); // sc, ec, fsc, fse, asc, aec, dc
+TEST(Stack, rangeCommandUnranged)
+{
+ tracker.reset();
+ logger.reset();
+
+ {
+ Stack s{parser, env.context, States::AnyHandlers};
+ tracker.expect(0, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
+ s.commandStart("a", {}, true);
+ tracker.expect(1, 0, 0, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
+ s.commandStart("b", {});
+ tracker.expect(2, 0, 1, 0, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
+ s.rangeEnd();
+ tracker.expect(2, 2, 1, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
+ }
+ tracker.expect(2, 2, 1, 1, 0); // scc, ec, fsc, fec, dc, sac, stc, etc
+ ASSERT_FALSE(logger.hasError());
+}
- s.fieldEnd();
- tracker.expect(2, 1, 3, 3, 0, 0, 2); // sc, ec, fsc, fse, asc, aec, dc
- }
- tracker.expect(2, 2, 3, 3, 0, 0, 2); // sc, ec, fsc, fse, asc, aec, dc
- ASSERT_FALSE(logger.hasError());
}
}
-} \ No newline at end of file
diff --git a/test/core/parser/stack/TokenRegistryTest.cpp b/test/core/parser/stack/TokenRegistryTest.cpp
new file mode 100644
index 0000000..20d6cd0
--- /dev/null
+++ b/test/core/parser/stack/TokenRegistryTest.cpp
@@ -0,0 +1,82 @@
+/*
+ Ousía
+ Copyright (C) 2014, 2015 Benjamin Paaßen, Andreas Stöckel
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>.
+*/
+
+#include <gtest/gtest.h>
+
+#include <core/parser/stack/Callbacks.hpp>
+#include <core/parser/stack/TokenRegistry.hpp>
+
+namespace ousia {
+namespace parser_stack {
+
+class ParserCallbacksProxy : public ParserCallbacks {
+public:
+ size_t registerTokenCount = 0;
+ size_t unregisterTokenCount = 0;
+
+ TokenId registerToken(const std::string &token) override
+ {
+ registerTokenCount++;
+ return registerTokenCount;
+ }
+
+ void unregisterToken(TokenId id) override { unregisterTokenCount++; }
+};
+
+TEST(TokenRegistry, simple)
+{
+ ParserCallbacksProxy parser;
+ {
+ TokenRegistry registry(parser);
+
+ ASSERT_EQ(0U, parser.registerTokenCount);
+ ASSERT_EQ(0U, parser.unregisterTokenCount);
+
+ ASSERT_EQ(1U, registry.registerToken("test"));
+ ASSERT_EQ(1U, registry.registerToken("test"));
+ ASSERT_EQ(2U, registry.registerToken("test2"));
+ ASSERT_EQ(2U, registry.registerToken("test2"));
+ ASSERT_EQ(3U, registry.registerToken("test3"));
+ ASSERT_EQ(3U, parser.registerTokenCount);
+ ASSERT_EQ(0U, parser.unregisterTokenCount);
+
+ registry.unregisterToken(1);
+ ASSERT_EQ(3U, parser.registerTokenCount);
+ ASSERT_EQ(0U, parser.unregisterTokenCount);
+
+ registry.unregisterToken(1);
+ ASSERT_EQ(3U, parser.registerTokenCount);
+ ASSERT_EQ(1U, parser.unregisterTokenCount);
+
+ registry.unregisterToken(1);
+ ASSERT_EQ(3U, parser.registerTokenCount);
+ ASSERT_EQ(1U, parser.unregisterTokenCount);
+
+ registry.unregisterToken(2);
+ ASSERT_EQ(3U, parser.registerTokenCount);
+ ASSERT_EQ(1U, parser.unregisterTokenCount);
+
+ registry.unregisterToken(2);
+ ASSERT_EQ(3U, parser.registerTokenCount);
+ ASSERT_EQ(2U, parser.unregisterTokenCount);
+ }
+ ASSERT_EQ(3U, parser.unregisterTokenCount);
+}
+}
+}
+
diff --git a/test/core/parser/utils/SourceOffsetVectorTest.cpp b/test/core/parser/utils/SourceOffsetVectorTest.cpp
index 25a4163..26254f9 100644
--- a/test/core/parser/utils/SourceOffsetVectorTest.cpp
+++ b/test/core/parser/utils/SourceOffsetVectorTest.cpp
@@ -51,7 +51,7 @@ TEST(SourceOffsetVector, gaps)
for (size_t i = 0; i < 999; i++) {
auto elem = vec.loadOffset(i);
EXPECT_EQ(i * 3 + 5, elem.first);
- EXPECT_EQ((i + 1) * 3 + 5, elem.second);
+ EXPECT_EQ(i * 3 + 7, elem.second);
}
auto elem = vec.loadOffset(999);
EXPECT_EQ(999U * 3 + 5, elem.first);
diff --git a/test/core/parser/utils/TokenizedDataTest.cpp b/test/core/parser/utils/TokenizedDataTest.cpp
index 231bad9..8488459 100644
--- a/test/core/parser/utils/TokenizedDataTest.cpp
+++ b/test/core/parser/utils/TokenizedDataTest.cpp
@@ -20,6 +20,8 @@
#include <core/parser/utils/TokenizedData.hpp>
+#include "TokenizedDataTestUtils.hpp"
+
namespace ousia {
TEST(TokenizedData, dataWhitespacePreserve)
@@ -29,15 +31,10 @@ TEST(TokenizedData, dataWhitespacePreserve)
// 0123456789012345
// 0 1
- Token token;
- ASSERT_TRUE(data.next(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(Tokens::Data, token.id);
- EXPECT_EQ(" test1 test2 ", token.content);
- EXPECT_EQ(0U, token.getLocation().getStart());
- EXPECT_EQ(16U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_FALSE(data.next(token, WhitespaceMode::PRESERVE));
+ TokenizedDataReader reader = data.reader();
+ assertText(reader, " test1 test2 ", TokenSet{}, WhitespaceMode::PRESERVE,
+ 0, 16);
+ assertEnd(reader);
}
TEST(TokenizedData, dataWhitespaceTrim)
@@ -47,15 +44,10 @@ TEST(TokenizedData, dataWhitespaceTrim)
// 0123456789012345
// 0 1
- Token token;
- ASSERT_TRUE(data.next(token, WhitespaceMode::TRIM));
- EXPECT_EQ(Tokens::Data, token.id);
- EXPECT_EQ("test1 test2", token.content);
- EXPECT_EQ(1U, token.getLocation().getStart());
- EXPECT_EQ(14U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_FALSE(data.next(token, WhitespaceMode::TRIM));
+ TokenizedDataReader reader = data.reader();
+ assertText(reader, "test1 test2", TokenSet{}, WhitespaceMode::TRIM, 1,
+ 14);
+ assertEnd(reader);
}
TEST(TokenizedData, dataWhitespaceCollapse)
@@ -65,15 +57,10 @@ TEST(TokenizedData, dataWhitespaceCollapse)
// 0123456789012345
// 0 1
- Token token;
- ASSERT_TRUE(data.next(token, WhitespaceMode::COLLAPSE));
- EXPECT_EQ(Tokens::Data, token.id);
- EXPECT_EQ("test1 test2", token.content);
- EXPECT_EQ(1U, token.getLocation().getStart());
- EXPECT_EQ(14U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_FALSE(data.next(token, WhitespaceMode::COLLAPSE));
+ TokenizedDataReader reader = data.reader();
+ assertText(reader, "test1 test2", TokenSet{}, WhitespaceMode::COLLAPSE, 1,
+ 14);
+ assertEnd(reader);
}
TEST(TokenizedData, singleToken)
@@ -82,17 +69,9 @@ TEST(TokenizedData, singleToken)
ASSERT_EQ(2U, data.append("$$"));
data.mark(5, 0, 2);
- data.enableToken(5);
-
- Token token;
- ASSERT_TRUE(data.next(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(5U, token.id);
- EXPECT_EQ("$$", token.content);
- EXPECT_EQ(0U, token.getLocation().getStart());
- EXPECT_EQ(2U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_FALSE(data.next(token, WhitespaceMode::PRESERVE));
+ TokenizedDataReader reader = data.reader();
+ assertToken(reader, 5, "$$", TokenSet{5}, WhitespaceMode::COLLAPSE, 0, 2);
+ assertEnd(reader);
}
TEST(TokenizedData, singleDisabledToken)
@@ -101,15 +80,9 @@ TEST(TokenizedData, singleDisabledToken)
ASSERT_EQ(2U, data.append("$$"));
data.mark(5, 0, 2);
- Token token;
- ASSERT_TRUE(data.next(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(Tokens::Data, token.id);
- EXPECT_EQ("$$", token.content);
- EXPECT_EQ(0U, token.getLocation().getStart());
- EXPECT_EQ(2U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_FALSE(data.next(token, WhitespaceMode::PRESERVE));
+ TokenizedDataReader reader = data.reader();
+ assertText(reader, "$$", TokenSet{}, WhitespaceMode::COLLAPSE, 0, 2);
+ assertEnd(reader);
}
TEST(TokenizedData, dualToken)
@@ -120,18 +93,10 @@ TEST(TokenizedData, dualToken)
data.mark(5, 0, 2);
data.mark(6, 1, 1);
- data.enableToken(5);
- data.enableToken(6);
-
- Token token;
- ASSERT_TRUE(data.next(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(5U, token.id);
- EXPECT_EQ("$$", token.content);
- EXPECT_EQ(0U, token.getLocation().getStart());
- EXPECT_EQ(2U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_FALSE(data.next(token, WhitespaceMode::PRESERVE));
+ TokenizedDataReader reader = data.reader();
+ assertToken(reader, 5, "$$", TokenSet{5, 6}, WhitespaceMode::COLLAPSE, 0,
+ 2);
+ assertEnd(reader);
}
TEST(TokenizedData, dualTokenShorterEnabled)
@@ -142,385 +107,281 @@ TEST(TokenizedData, dualTokenShorterEnabled)
data.mark(5, 0, 2);
data.mark(6, 1, 1);
- data.enableToken(6);
-
- Token token;
- ASSERT_TRUE(data.next(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(6U, token.id);
- EXPECT_EQ("$", token.content);
- EXPECT_EQ(0U, token.getLocation().getStart());
- EXPECT_EQ(1U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_TRUE(data.next(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(6U, token.id);
- EXPECT_EQ("$", token.content);
- EXPECT_EQ(1U, token.getLocation().getStart());
- EXPECT_EQ(2U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_FALSE(data.next(token, WhitespaceMode::PRESERVE));
+ TokenizedDataReader reader = data.reader();
+ assertToken(reader, 6, "$", TokenSet{6}, WhitespaceMode::COLLAPSE, 0, 1);
+ assertToken(reader, 6, "$", TokenSet{6}, WhitespaceMode::COLLAPSE, 1, 2);
+ assertEnd(reader);
}
TEST(TokenizedData, dualTokenLongerEnabled)
{
TokenizedData data;
ASSERT_EQ(2U, data.append("$$"));
+ data.mark(6, 0, 1);
data.mark(5, 0, 2);
+ data.mark(6, 1, 1);
- data.enableToken(5);
-
- Token token;
- ASSERT_TRUE(data.next(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(5U, token.id);
- EXPECT_EQ("$$", token.content);
- EXPECT_EQ(0U, token.getLocation().getStart());
- EXPECT_EQ(2U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_FALSE(data.next(token, WhitespaceMode::PRESERVE));
+ TokenizedDataReader reader = data.reader();
+ assertToken(reader, 5, "$$", TokenSet{5}, WhitespaceMode::COLLAPSE, 0, 2);
+ assertEnd(reader);
}
TEST(TokenizedData, tokensAndDataPreserveWhitespace)
{
TokenizedData data;
- ASSERT_EQ(10U, data.append("$$ test $$"));
- // 0123456789
+ ASSERT_EQ(18U, data.append("$$ test text $$"));
+ // 012345678901234567
data.mark(5, 0, 2);
data.mark(5, 2);
- data.enableToken(5);
-
- Token token;
- ASSERT_TRUE(data.next(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(5U, token.id);
- EXPECT_EQ("$$", token.content);
- EXPECT_EQ(0U, token.getLocation().getStart());
- EXPECT_EQ(2U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_TRUE(data.next(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(Tokens::Data, token.id);
- EXPECT_EQ(" test ", token.content);
- EXPECT_EQ(2U, token.getLocation().getStart());
- EXPECT_EQ(8U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_TRUE(data.next(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(5U, token.id);
- EXPECT_EQ("$$", token.content);
- EXPECT_EQ(8U, token.getLocation().getStart());
- EXPECT_EQ(10U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_FALSE(data.next(token, WhitespaceMode::PRESERVE));
+ TokenizedDataReader reader = data.reader();
+ assertToken(reader, 5, "$$", TokenSet{5}, WhitespaceMode::PRESERVE, 0, 2);
+ assertText(reader, " test text ", TokenSet{5}, WhitespaceMode::PRESERVE,
+ 2, 16);
+ assertToken(reader, 5, "$$", TokenSet{5}, WhitespaceMode::PRESERVE, 16, 18);
+ assertEnd(reader);
}
TEST(TokenizedData, tokensAndDataTrimWhitespace)
{
TokenizedData data;
- ASSERT_EQ(10U, data.append("$$ test $$"));
- // 0123456789
+ ASSERT_EQ(18U, data.append("$$ test text $$"));
+ // 012345678901234567
data.mark(5, 0, 2);
data.mark(5, 2);
- data.enableToken(5);
-
- Token token;
- ASSERT_TRUE(data.next(token, WhitespaceMode::TRIM));
- EXPECT_EQ(5U, token.id);
- EXPECT_EQ("$$", token.content);
- EXPECT_EQ(0U, token.getLocation().getStart());
- EXPECT_EQ(2U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_TRUE(data.next(token, WhitespaceMode::TRIM));
- EXPECT_EQ(Tokens::Data, token.id);
- EXPECT_EQ("test", token.content);
- EXPECT_EQ(3U, token.getLocation().getStart());
- EXPECT_EQ(7U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_TRUE(data.next(token, WhitespaceMode::TRIM));
- EXPECT_EQ(5U, token.id);
- EXPECT_EQ("$$", token.content);
- EXPECT_EQ(8U, token.getLocation().getStart());
- EXPECT_EQ(10U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_FALSE(data.next(token, WhitespaceMode::TRIM));
+ TokenizedDataReader reader = data.reader();
+ assertToken(reader, 5, "$$", TokenSet{5}, WhitespaceMode::TRIM, 0, 2);
+ assertText(reader, "test text", TokenSet{5}, WhitespaceMode::TRIM, 3,
+ 15);
+ assertToken(reader, 5, "$$", TokenSet{5}, WhitespaceMode::TRIM, 16, 18);
+ assertEnd(reader);
}
TEST(TokenizedData, tokensAndDataCollapseWhitespace)
{
TokenizedData data;
- ASSERT_EQ(10U, data.append("$$ test $$"));
- // 0123456789
+ ASSERT_EQ(18U, data.append("$$ test text $$"));
+ // 012345678901234567
data.mark(5, 0, 2);
data.mark(5, 2);
- data.enableToken(5);
-
- Token token;
- ASSERT_TRUE(data.next(token, WhitespaceMode::COLLAPSE));
- EXPECT_EQ(5U, token.id);
- EXPECT_EQ("$$", token.content);
- EXPECT_EQ(0U, token.getLocation().getStart());
- EXPECT_EQ(2U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_TRUE(data.next(token, WhitespaceMode::COLLAPSE));
- EXPECT_EQ(Tokens::Data, token.id);
- EXPECT_EQ("test", token.content);
- EXPECT_EQ(3U, token.getLocation().getStart());
- EXPECT_EQ(7U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_TRUE(data.next(token, WhitespaceMode::COLLAPSE));
- EXPECT_EQ(5U, token.id);
- EXPECT_EQ("$$", token.content);
- EXPECT_EQ(8U, token.getLocation().getStart());
- EXPECT_EQ(10U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_FALSE(data.next(token, WhitespaceMode::COLLAPSE));
+ TokenizedDataReader reader = data.reader();
+ assertToken(reader, 5, "$$", TokenSet{5}, WhitespaceMode::COLLAPSE, 0, 2);
+ assertText(reader, "test text", TokenSet{5}, WhitespaceMode::COLLAPSE, 3,
+ 15);
+ assertToken(reader, 5, "$$", TokenSet{5}, WhitespaceMode::COLLAPSE, 16, 18);
+ assertEnd(reader);
}
TEST(TokenizedData, tokensAndWhitespacePreserveWhitespace)
{
TokenizedData data;
- ASSERT_EQ(10U, data.append("$$ $$"));
- // 0123456789
+ ASSERT_EQ(8U, data.append("$$ $$"));
+ // 01234567
data.mark(5, 0, 2);
data.mark(5, 2);
- data.enableToken(5);
-
- Token token;
- ASSERT_TRUE(data.next(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(0U, token.getLocation().getStart());
- EXPECT_EQ(2U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_TRUE(data.next(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(Tokens::Data, token.id);
- EXPECT_EQ(" ", token.content);
- EXPECT_EQ(2U, token.getLocation().getStart());
- EXPECT_EQ(8U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_TRUE(data.next(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(5U, token.id);
- EXPECT_EQ("$$", token.content);
- EXPECT_EQ(8U, token.getLocation().getStart());
- EXPECT_EQ(10U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_FALSE(data.next(token, WhitespaceMode::PRESERVE));
+ TokenizedDataReader reader = data.reader();
+ assertToken(reader, 5, "$$", TokenSet{5}, WhitespaceMode::PRESERVE, 0, 2);
+ assertText(reader, " ", TokenSet{5}, WhitespaceMode::PRESERVE, 2, 6);
+ assertToken(reader, 5, "$$", TokenSet{5}, WhitespaceMode::PRESERVE, 6, 8);
+ assertEnd(reader);
}
TEST(TokenizedData, tokensAndWhitespaceTrimWhitespace)
{
TokenizedData data;
- ASSERT_EQ(10U, data.append("$$ $$"));
- // 0123456789
+ ASSERT_EQ(8U, data.append("$$ $$"));
+ // 01234567
data.mark(5, 0, 2);
data.mark(5, 2);
- data.enableToken(5);
-
- Token token;
- ASSERT_TRUE(data.next(token, WhitespaceMode::TRIM));
- EXPECT_EQ(0U, token.getLocation().getStart());
- EXPECT_EQ(2U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_TRUE(data.next(token, WhitespaceMode::TRIM));
- EXPECT_EQ(5U, token.id);
- EXPECT_EQ("$$", token.content);
- EXPECT_EQ(8U, token.getLocation().getStart());
- EXPECT_EQ(10U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_FALSE(data.next(token, WhitespaceMode::TRIM));
+ TokenizedDataReader reader = data.reader();
+ assertToken(reader, 5, "$$", TokenSet{5}, WhitespaceMode::TRIM, 0, 2);
+ assertToken(reader, 5, "$$", TokenSet{5}, WhitespaceMode::TRIM, 6, 8);
+ assertEnd(reader);
}
TEST(TokenizedData, tokensAndWhitespaceCollapseWhitespace)
{
TokenizedData data;
- ASSERT_EQ(10U, data.append("$$ $$"));
- // 0123456789
+ ASSERT_EQ(8U, data.append("$$ $$"));
+ // 01234567
data.mark(5, 0, 2);
data.mark(5, 2);
- data.enableToken(5);
-
- Token token;
- ASSERT_TRUE(data.next(token, WhitespaceMode::COLLAPSE));
- EXPECT_EQ(0U, token.getLocation().getStart());
- EXPECT_EQ(2U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
+ TokenizedDataReader reader = data.reader();
+ assertToken(reader, 5, "$$", TokenSet{5}, WhitespaceMode::COLLAPSE, 0, 2);
+ assertToken(reader, 5, "$$", TokenSet{5}, WhitespaceMode::COLLAPSE, 6, 8);
+ assertEnd(reader);
+}
- ASSERT_TRUE(data.next(token, WhitespaceMode::COLLAPSE));
- EXPECT_EQ(5U, token.id);
- EXPECT_EQ("$$", token.content);
- EXPECT_EQ(8U, token.getLocation().getStart());
- EXPECT_EQ(10U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
+TEST(TokenizedData, appendChars)
+{
+ TokenizedData data;
+ ASSERT_EQ(1U, data.append('t', 5, 7));
+ ASSERT_EQ(2U, data.append('e', 7, 8));
+ ASSERT_EQ(3U, data.append('s', 8, 10));
+ ASSERT_EQ(4U, data.append('t', 10, 12));
- ASSERT_FALSE(data.next(token, WhitespaceMode::COLLAPSE));
+ TokenizedDataReader reader = data.reader();
+ assertText(reader, "test", TokenSet{5}, WhitespaceMode::COLLAPSE, 5, 12);
+ assertEnd(reader);
}
-TEST(TokenizedData, textPreserveWhitespace)
+TEST(TokenizedData, protectedWhitespace)
{
TokenizedData data;
- ASSERT_EQ(6U, data.append(" $$ "));
- // 012345
- data.mark(5, 2, 2);
-
- data.enableToken(5);
-
- Token token;
- ASSERT_TRUE(data.text(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(Tokens::Data, token.id);
- EXPECT_EQ(" ", token.content);
- EXPECT_EQ(0U, token.getLocation().getStart());
- EXPECT_EQ(2U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_TRUE(data.next(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(5U, token.id);
- EXPECT_EQ("$$", token.content);
- EXPECT_EQ(2U, token.getLocation().getStart());
- EXPECT_EQ(4U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_TRUE(data.text(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(Tokens::Data, token.id);
- EXPECT_EQ(" ", token.content);
- EXPECT_EQ(4U, token.getLocation().getStart());
- EXPECT_EQ(6U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_FALSE(data.text(token, WhitespaceMode::PRESERVE));
- ASSERT_FALSE(data.next(token, WhitespaceMode::PRESERVE));
+ ASSERT_EQ(4U, data.append("test", 10));
+ ASSERT_EQ(11U, data.append(" test", 14, true));
+
+ TokenizedDataReader reader = data.reader();
+ assertText(reader, "test test", TokenSet{5}, WhitespaceMode::COLLAPSE, 10,
+ 21);
+ assertEnd(reader);
}
-TEST(TokenizedData, textTrimWhitespace)
+TEST(TokenizedData, specialNewlineToken)
{
TokenizedData data;
- ASSERT_EQ(6U, data.append(" $$ "));
- // 012345
- data.mark(5, 2, 2);
-
- data.enableToken(5);
+ data.append("a\nb\n \nc\n");
+ // 0 12 3456 78 9
+
+ const TokenSet tokens{Tokens::Newline};
+
+ TokenizedDataReader reader = data.reader();
+ assertText(reader, "a", tokens, WhitespaceMode::COLLAPSE, 0, 1);
+ assertToken(reader, Tokens::Newline, "\n", tokens, WhitespaceMode::COLLAPSE,
+ 1, 2);
+ assertText(reader, "b", tokens, WhitespaceMode::COLLAPSE, 2, 3);
+ assertToken(reader, Tokens::Newline, "\n", tokens, WhitespaceMode::COLLAPSE,
+ 3, 4);
+ assertToken(reader, Tokens::Newline, "\n", tokens, WhitespaceMode::COLLAPSE,
+ 7, 8);
+ assertText(reader, "c", tokens, WhitespaceMode::COLLAPSE, 8, 9);
+ assertToken(reader, Tokens::Newline, "\n", tokens, WhitespaceMode::COLLAPSE,
+ 9, 10);
+ assertEnd(reader);
+}
- Token token;
- ASSERT_FALSE(data.text(token, WhitespaceMode::TRIM));
+TEST(TokenizedData, specialParagraphToken)
+{
+ TokenizedData data;
+ data.append("a\nb\n \nc\n");
+ // 0 12 3456 78 9
- ASSERT_TRUE(data.next(token, WhitespaceMode::TRIM));
- EXPECT_EQ(5U, token.id);
- EXPECT_EQ("$$", token.content);
- EXPECT_EQ(2U, token.getLocation().getStart());
- EXPECT_EQ(4U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
+ const TokenSet tokens{Tokens::Paragraph};
- ASSERT_FALSE(data.text(token, WhitespaceMode::TRIM));
- ASSERT_FALSE(data.next(token, WhitespaceMode::TRIM));
+ TokenizedDataReader reader = data.reader();
+ assertText(reader, "a b", tokens, WhitespaceMode::COLLAPSE, 0, 3);
+ assertToken(reader, Tokens::Paragraph, "\n \n", tokens,
+ WhitespaceMode::COLLAPSE, 3, 8);
+ assertText(reader, "c", tokens, WhitespaceMode::COLLAPSE, 8, 9);
+ assertEnd(reader);
}
-TEST(TokenizedData, textCollapseWhitespace)
+TEST(TokenizedData, specialSectionToken)
{
TokenizedData data;
- ASSERT_EQ(6U, data.append(" $$ "));
- // 012345
- data.mark(5, 2, 2);
+ data.append("a\nb\n \n \t \n");
+ // 0 12 3456 789 01 2
+ // 0 1
- data.enableToken(5);
+ const TokenSet tokens{Tokens::Section};
- Token token;
- ASSERT_FALSE(data.text(token, WhitespaceMode::COLLAPSE));
-
- ASSERT_TRUE(data.next(token, WhitespaceMode::COLLAPSE));
- EXPECT_EQ(5U, token.id);
- EXPECT_EQ("$$", token.content);
- EXPECT_EQ(2U, token.getLocation().getStart());
- EXPECT_EQ(4U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_FALSE(data.text(token, WhitespaceMode::COLLAPSE));
- ASSERT_FALSE(data.next(token, WhitespaceMode::COLLAPSE));
+ TokenizedDataReader reader = data.reader();
+ assertText(reader, "a b", tokens, WhitespaceMode::COLLAPSE, 0, 3);
+ assertToken(reader, Tokens::Section, "\n \n \t \n", tokens,
+ WhitespaceMode::COLLAPSE, 3, 13);
+ assertEnd(reader);
}
-TEST(TokenizedData, appendChars)
+TEST(TokenizedData, specialTokenPrecedence)
{
TokenizedData data;
- ASSERT_EQ(1U, data.append('t', 5, 7));
- ASSERT_EQ(2U, data.append('e', 7, 8));
- ASSERT_EQ(3U, data.append('s', 8, 10));
- ASSERT_EQ(4U, data.append('t', 10, 12));
+ data.append("a\nb\n\nc\n\n\nd");
+ // 0 12 3 45 6 7 89
+
+ const TokenSet tokens{Tokens::Newline, Tokens::Paragraph, Tokens::Section};
+
+ TokenizedDataReader reader = data.reader();
+ assertText(reader, "a", tokens, WhitespaceMode::COLLAPSE, 0, 1);
+ assertToken(reader, Tokens::Newline, "\n", tokens, WhitespaceMode::COLLAPSE,
+ 1, 2);
+ assertText(reader, "b", tokens, WhitespaceMode::COLLAPSE, 2, 3);
+ assertToken(reader, Tokens::Paragraph, "\n\n", tokens,
+ WhitespaceMode::COLLAPSE, 3, 5);
+ assertText(reader, "c", tokens, WhitespaceMode::COLLAPSE, 5, 6);
+ assertToken(reader, Tokens::Section, "\n\n\n", tokens,
+ WhitespaceMode::COLLAPSE, 6, 9);
+ assertText(reader, "d", tokens, WhitespaceMode::COLLAPSE, 9, 10);
+ assertEnd(reader);
+}
- Token token;
- ASSERT_TRUE(data.text(token, WhitespaceMode::COLLAPSE));
- EXPECT_EQ(Tokens::Data, token.id);
- EXPECT_EQ("test", token.content);
- EXPECT_EQ(5U, token.getLocation().getStart());
- EXPECT_EQ(12U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
+TEST(TokenizedData, specialTokenPrecedence2)
+{
+ TokenizedData data;
+ data.append("\nb\n\nc\n\n\n");
+ // 0 12 3 45 6 7
+
+ const TokenSet tokens{Tokens::Newline, Tokens::Paragraph, Tokens::Section};
+
+ TokenizedDataReader reader = data.reader();
+ assertToken(reader, Tokens::Newline, "\n", tokens, WhitespaceMode::COLLAPSE,
+ 0, 1);
+ assertText(reader, "b", tokens, WhitespaceMode::COLLAPSE, 1, 2);
+ assertToken(reader, Tokens::Paragraph, "\n\n", tokens,
+ WhitespaceMode::COLLAPSE, 2, 4);
+ assertText(reader, "c", tokens, WhitespaceMode::COLLAPSE, 4, 5);
+ assertToken(reader, Tokens::Section, "\n\n\n", tokens,
+ WhitespaceMode::COLLAPSE, 5, 8);
+ assertEnd(reader);
+}
- ASSERT_FALSE(data.text(token, WhitespaceMode::COLLAPSE));
- ASSERT_FALSE(data.next(token, WhitespaceMode::COLLAPSE));
+TEST(TokenizedData, specialTokenIndent)
+{
+ TokenizedData data;
+ data.append(" test\n\ttest2\n test3 \ttest4\ntest5");
+ // 01234567 8 901234 5678901234567890 123456 789012
+ // 0 1 2 3 4
+ const TokenSet tokens{Tokens::Indent, Tokens::Dedent};
+
+ TokenizedDataReader reader = data.reader();
+ assertToken(reader, Tokens::Indent, "", tokens, WhitespaceMode::COLLAPSE,
+ 4, 4);
+ assertText(reader, "test", tokens, WhitespaceMode::COLLAPSE, 4, 8);
+ assertToken(reader, Tokens::Indent, "", tokens, WhitespaceMode::COLLAPSE,
+ 10, 10);
+ assertText(reader, "test2 test3 test4", tokens, WhitespaceMode::COLLAPSE, 10, 37);
+ assertToken(reader, Tokens::Dedent, "", tokens, WhitespaceMode::COLLAPSE,
+ 38, 38);
+ assertText(reader, "test5", tokens, WhitespaceMode::COLLAPSE, 38, 43);
+ assertEnd(reader);
}
-TEST(TokenizedData, copy)
+TEST(TokenizedData, specialTokenIndentOverlap)
{
TokenizedData data;
- ASSERT_EQ(7U, data.append(" a $ b "));
- // 0123456
- data.mark(6, 3, 1);
- data.enableToken(6);
-
- Token token;
- ASSERT_TRUE(data.text(token, WhitespaceMode::COLLAPSE));
- EXPECT_EQ(Tokens::Data, token.id);
- EXPECT_EQ("a", token.content);
- EXPECT_EQ(1U, token.getLocation().getStart());
- EXPECT_EQ(2U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_FALSE(data.text(token, WhitespaceMode::COLLAPSE));
-
- TokenizedData dataCopy = data;
-
- ASSERT_TRUE(data.next(token, WhitespaceMode::COLLAPSE));
- EXPECT_EQ(6U, token.id);
- EXPECT_EQ("$", token.content);
- EXPECT_EQ(3U, token.getLocation().getStart());
- EXPECT_EQ(4U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_TRUE(dataCopy.next(token, WhitespaceMode::COLLAPSE));
- EXPECT_EQ(6U, token.id);
- EXPECT_EQ("$", token.content);
- EXPECT_EQ(3U, token.getLocation().getStart());
- EXPECT_EQ(4U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
-
- ASSERT_TRUE(data.text(token, WhitespaceMode::PRESERVE));
- EXPECT_EQ(Tokens::Data, token.id);
- EXPECT_EQ(" b ", token.content);
- EXPECT_EQ(4U, token.getLocation().getStart());
- EXPECT_EQ(7U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
- ASSERT_FALSE(data.next(token));
-
- ASSERT_TRUE(dataCopy.text(token, WhitespaceMode::COLLAPSE));
- EXPECT_EQ(Tokens::Data, token.id);
- EXPECT_EQ("b", token.content);
- EXPECT_EQ(5U, token.getLocation().getStart());
- EXPECT_EQ(6U, token.getLocation().getEnd());
- EXPECT_EQ(InvalidSourceId, token.getLocation().getSourceId());
- ASSERT_FALSE(dataCopy.next(token));
+ data.append(" test\n\ttest2\n test3 \ttest4\ntest5");
+ // 01234567 8 901234 5678901234567890 123456 789012
+ // 0 1 2 3 4
+ const TokenSet tokens{Tokens::Indent, Tokens::Dedent, 5};
+
+ data.mark(5, 4, 4);
+
+ TokenizedDataReader reader = data.reader();
+ assertToken(reader, Tokens::Indent, "", tokens, WhitespaceMode::COLLAPSE,
+ 4, 4);
+ assertToken(reader, 5, "test", tokens, WhitespaceMode::COLLAPSE, 4, 8);
+ assertToken(reader, Tokens::Indent, "", tokens, WhitespaceMode::COLLAPSE,
+ 10, 10);
+ assertText(reader, "test2 test3 test4", tokens, WhitespaceMode::COLLAPSE, 10, 37);
+ assertToken(reader, Tokens::Dedent, "", tokens, WhitespaceMode::COLLAPSE,
+ 38, 38);
+ assertText(reader, "test5", tokens, WhitespaceMode::COLLAPSE, 38, 43);
+ assertEnd(reader);
}
+
}
diff --git a/test/core/parser/utils/TokenizedDataTestUtils.hpp b/test/core/parser/utils/TokenizedDataTestUtils.hpp
new file mode 100644
index 0000000..c384f9d
--- /dev/null
+++ b/test/core/parser/utils/TokenizedDataTestUtils.hpp
@@ -0,0 +1,64 @@
+/*
+ Ousía
+ Copyright (C) 2014, 2015 Benjamin Paaßen, Andreas Stöckel
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>.
+*/
+
+#ifndef _OUSIA_TOKENIZED_DATA_TEST_UTILS_HPP_
+#define _OUSIA_TOKENIZED_DATA_TEST_UTILS_HPP_
+
+namespace ousia {
+
+static void assertToken(TokenizedDataReader &reader, TokenId id,
+ const std::string &text, const TokenSet &tokens = TokenSet{},
+ WhitespaceMode mode = WhitespaceMode::TRIM,
+ SourceOffset start = InvalidSourceOffset,
+ SourceOffset end = InvalidSourceOffset,
+ SourceId sourceId = InvalidSourceId)
+{
+ Token token;
+ ASSERT_TRUE(reader.read(token, tokens, mode));
+ EXPECT_EQ(id, token.id);
+ EXPECT_EQ(text, token.content);
+ if (start != InvalidSourceOffset) {
+ EXPECT_EQ(start, token.getLocation().getStart());
+ }
+ if (end != InvalidSourceOffset) {
+ EXPECT_EQ(end, token.getLocation().getEnd());
+ }
+ EXPECT_EQ(sourceId, token.getLocation().getSourceId());
+}
+
+static void assertText(TokenizedDataReader &reader, const std::string &text,
+ const TokenSet &tokens = TokenSet{},
+ WhitespaceMode mode = WhitespaceMode::TRIM,
+ SourceOffset start = InvalidSourceOffset,
+ SourceOffset end = InvalidSourceOffset,
+ SourceId id = InvalidSourceId)
+{
+ assertToken(reader, Tokens::Data, text, tokens, mode, start, end, id);
+}
+
+static void assertEnd(TokenizedDataReader &reader)
+{
+ Token token;
+ ASSERT_TRUE(reader.atEnd());
+ ASSERT_FALSE(reader.read(token));
+}
+
+}
+
+#endif /* _OUSIA_TOKENIZED_DATA_TEST_UTILS_HPP_ */
+
diff --git a/test/core/parser/utils/TokenizerTest.cpp b/test/core/parser/utils/TokenizerTest.cpp
index 3809a12..45fc77a 100644
--- a/test/core/parser/utils/TokenizerTest.cpp
+++ b/test/core/parser/utils/TokenizerTest.cpp
@@ -20,9 +20,66 @@
#include <core/common/CharReader.hpp>
#include <core/parser/utils/Tokenizer.hpp>
+#include <core/parser/utils/TokenizedData.hpp>
+
+#include "TokenizedDataTestUtils.hpp"
namespace ousia {
+static void assertPrimaryToken(CharReader &reader, Tokenizer &tokenizer,
+ TokenId id, const std::string &text,
+ SourceOffset start = InvalidSourceOffset,
+ SourceOffset end = InvalidSourceOffset,
+ SourceId sourceId = InvalidSourceId)
+{
+ Token token;
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
+ EXPECT_EQ(id, token.id);
+ EXPECT_EQ(text, token.content);
+ if (start != InvalidSourceOffset) {
+ EXPECT_EQ(start, token.getLocation().getStart());
+ }
+ if (end != InvalidSourceOffset) {
+ EXPECT_EQ(end, token.getLocation().getEnd());
+ }
+ EXPECT_EQ(sourceId, token.getLocation().getSourceId());
+}
+
+static void expectData(const std::string &expected, SourceOffset tokenStart,
+ SourceOffset tokenEnd, SourceOffset textStart,
+ SourceOffset textEnd, const Token &token,
+ TokenizedData &data,
+ WhitespaceMode mode = WhitespaceMode::PRESERVE)
+{
+ ASSERT_EQ(Tokens::Data, token.id);
+
+ Token textToken;
+ TokenizedDataReader reader = data.reader();
+ ASSERT_TRUE(reader.read(textToken, TokenSet{}, mode));
+
+ EXPECT_EQ(expected, textToken.content);
+ EXPECT_EQ(tokenStart, token.location.getStart());
+ EXPECT_EQ(tokenEnd, token.location.getEnd());
+ EXPECT_EQ(textStart, textToken.getLocation().getStart());
+ EXPECT_EQ(textEnd, textToken.getLocation().getEnd());
+ EXPECT_TRUE(reader.atEnd());
+}
+
+static void assertDataToken(CharReader &reader, Tokenizer &tokenizer,
+ const std::string &expected,
+ SourceOffset tokenStart, SourceOffset tokenEnd,
+ SourceOffset textStart, SourceOffset textEnd,
+ WhitespaceMode mode = WhitespaceMode::PRESERVE)
+{
+ Token token;
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
+
+ expectData(expected, tokenStart, tokenEnd, textStart, textEnd, token, data,
+ mode);
+}
+
TEST(Tokenizer, tokenRegistration)
{
Tokenizer tokenizer;
@@ -31,23 +88,23 @@ TEST(Tokenizer, tokenRegistration)
ASSERT_EQ(0U, tokenizer.registerToken("a"));
ASSERT_EQ(Tokens::Empty, tokenizer.registerToken("a"));
- ASSERT_EQ("a", tokenizer.getTokenString(0U));
+ ASSERT_EQ("a", tokenizer.lookupToken(0U).string);
ASSERT_EQ(1U, tokenizer.registerToken("b"));
ASSERT_EQ(Tokens::Empty, tokenizer.registerToken("b"));
- ASSERT_EQ("b", tokenizer.getTokenString(1U));
+ ASSERT_EQ("b", tokenizer.lookupToken(1U).string);
ASSERT_EQ(2U, tokenizer.registerToken("c"));
ASSERT_EQ(Tokens::Empty, tokenizer.registerToken("c"));
- ASSERT_EQ("c", tokenizer.getTokenString(2U));
+ ASSERT_EQ("c", tokenizer.lookupToken(2U).string);
ASSERT_TRUE(tokenizer.unregisterToken(1U));
ASSERT_FALSE(tokenizer.unregisterToken(1U));
- ASSERT_EQ("", tokenizer.getTokenString(1U));
+ ASSERT_EQ("", tokenizer.lookupToken(1U).string);
ASSERT_EQ(1U, tokenizer.registerToken("d"));
ASSERT_EQ(Tokens::Empty, tokenizer.registerToken("d"));
- ASSERT_EQ("d", tokenizer.getTokenString(1U));
+ ASSERT_EQ("d", tokenizer.lookupToken(1U).string);
}
TEST(Tokenizer, textTokenPreserveWhitespace)
@@ -56,36 +113,34 @@ TEST(Tokenizer, textTokenPreserveWhitespace)
CharReader reader{" this \t is only a \n\n test text "};
// 012345 6789012345678 9 0123456789012345
// 0 1 2 3
- Tokenizer tokenizer{WhitespaceMode::PRESERVE};
+ Tokenizer tokenizer;
Token token;
- ASSERT_TRUE(tokenizer.read(reader, token));
- ASSERT_EQ(Tokens::Data, token.id);
- ASSERT_EQ(" this \t is only a \n\n test text ", token.content);
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
- SourceLocation loc = token.location;
- ASSERT_EQ(0U, loc.getStart());
- ASSERT_EQ(36U, loc.getEnd());
+ expectData(" this \t is only a \n\n test text ", 0, 36, 0, 36,
+ token, data, WhitespaceMode::PRESERVE);
- ASSERT_FALSE(tokenizer.read(reader, token));
+ data.clear();
+ ASSERT_FALSE(tokenizer.read(reader, token, data));
}
{
CharReader reader{"this \t is only a \n\n test text"};
// 01234 5678901234567 8 9012345678901
// 0 1 2 3
- Tokenizer tokenizer{WhitespaceMode::PRESERVE};
+ Tokenizer tokenizer;
Token token;
- ASSERT_TRUE(tokenizer.read(reader, token));
- ASSERT_EQ(Tokens::Data, token.id);
- ASSERT_EQ("this \t is only a \n\n test text", token.content);
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
- SourceLocation loc = token.location;
- ASSERT_EQ(0U, loc.getStart());
- ASSERT_EQ(32U, loc.getEnd());
+ expectData("this \t is only a \n\n test text", 0, 32, 0, 32, token,
+ data, WhitespaceMode::PRESERVE);
- ASSERT_FALSE(tokenizer.read(reader, token));
+ data.clear();
+ ASSERT_FALSE(tokenizer.read(reader, token, data));
}
}
@@ -95,36 +150,34 @@ TEST(Tokenizer, textTokenTrimWhitespace)
CharReader reader{" this \t is only a \n\n test text "};
// 012345 6789012345678 9 0123456789012345
// 0 1 2 3
- Tokenizer tokenizer{WhitespaceMode::TRIM};
+ Tokenizer tokenizer;
Token token;
- ASSERT_TRUE(tokenizer.read(reader, token));
- ASSERT_EQ(Tokens::Data, token.id);
- ASSERT_EQ("this \t is only a \n\n test text", token.content);
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
- SourceLocation loc = token.location;
- ASSERT_EQ(1U, loc.getStart());
- ASSERT_EQ(33U, loc.getEnd());
+ expectData("this \t is only a \n\n test text", 0, 36, 1, 33, token,
+ data, WhitespaceMode::TRIM);
- ASSERT_FALSE(tokenizer.read(reader, token));
+ data.clear();
+ ASSERT_FALSE(tokenizer.read(reader, token, data));
}
{
CharReader reader{"this \t is only a \n\n test text"};
// 01234 5678901234567 8 9012345678901
// 0 1 2 3
- Tokenizer tokenizer{WhitespaceMode::TRIM};
+ Tokenizer tokenizer;
Token token;
- ASSERT_TRUE(tokenizer.read(reader, token));
- ASSERT_EQ(Tokens::Data, token.id);
- ASSERT_EQ("this \t is only a \n\n test text", token.content);
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
- SourceLocation loc = token.location;
- ASSERT_EQ(0U, loc.getStart());
- ASSERT_EQ(32U, loc.getEnd());
+ expectData("this \t is only a \n\n test text", 0, 32, 0, 32, token,
+ data, WhitespaceMode::TRIM);
- ASSERT_FALSE(tokenizer.read(reader, token));
+ data.clear();
+ ASSERT_FALSE(tokenizer.read(reader, token, data));
}
}
@@ -134,36 +187,34 @@ TEST(Tokenizer, textTokenCollapseWhitespace)
CharReader reader{" this \t is only a \n\n test text "};
// 012345 6789012345678 9 0123456789012345
// 0 1 2 3
- Tokenizer tokenizer{WhitespaceMode::COLLAPSE};
+ Tokenizer tokenizer;
Token token;
- ASSERT_TRUE(tokenizer.read(reader, token));
- ASSERT_EQ(Tokens::Data, token.id);
- ASSERT_EQ("this is only a test text", token.content);
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
- SourceLocation loc = token.location;
- ASSERT_EQ(1U, loc.getStart());
- ASSERT_EQ(33U, loc.getEnd());
+ expectData("this is only a test text", 0, 36, 1, 33, token, data,
+ WhitespaceMode::COLLAPSE);
- ASSERT_FALSE(tokenizer.read(reader, token));
+ data.clear();
+ ASSERT_FALSE(tokenizer.read(reader, token, data));
}
{
CharReader reader{"this \t is only a \n\n test text"};
// 01234 5678901234567 8 9012345678901
// 0 1 2 3
- Tokenizer tokenizer{WhitespaceMode::COLLAPSE};
+ Tokenizer tokenizer;
Token token;
- ASSERT_TRUE(tokenizer.read(reader, token));
- ASSERT_EQ(Tokens::Data, token.id);
- ASSERT_EQ("this is only a test text", token.content);
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
- SourceLocation loc = token.location;
- ASSERT_EQ(0U, loc.getStart());
- ASSERT_EQ(32U, loc.getEnd());
+ expectData("this is only a test text", 0, 32, 0, 32, token, data,
+ WhitespaceMode::COLLAPSE);
- ASSERT_FALSE(tokenizer.read(reader, token));
+ data.clear();
+ ASSERT_FALSE(tokenizer.read(reader, token, data));
}
}
@@ -177,14 +228,12 @@ TEST(Tokenizer, simpleReadToken)
{
Token token;
- ASSERT_TRUE(tokenizer.read(reader, token));
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
ASSERT_EQ(Tokens::Data, token.id);
- ASSERT_EQ("test1", token.content);
- SourceLocation loc = token.location;
- ASSERT_EQ(0U, loc.getStart());
- ASSERT_EQ(5U, loc.getEnd());
+ expectData("test1", 0, 5, 0, 5, token, data);
char c;
ASSERT_TRUE(reader.peek(c));
@@ -193,7 +242,8 @@ TEST(Tokenizer, simpleReadToken)
{
Token token;
- ASSERT_TRUE(tokenizer.read(reader, token));
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
ASSERT_EQ(tid, token.id);
ASSERT_EQ(":", token.content);
@@ -209,14 +259,10 @@ TEST(Tokenizer, simpleReadToken)
{
Token token;
- ASSERT_TRUE(tokenizer.read(reader, token));
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
- ASSERT_EQ(Tokens::Data, token.id);
- ASSERT_EQ("test2", token.content);
-
- SourceLocation loc = token.location;
- ASSERT_EQ(6U, loc.getStart());
- ASSERT_EQ(11U, loc.getEnd());
+ expectData("test2", 6, 11, 6, 11, token, data);
char c;
ASSERT_FALSE(reader.peek(c));
@@ -233,21 +279,17 @@ TEST(Tokenizer, simplePeekToken)
{
Token token;
- ASSERT_TRUE(tokenizer.peek(reader, token));
-
- ASSERT_EQ(Tokens::Data, token.id);
- ASSERT_EQ("test1", token.content);
-
- SourceLocation loc = token.location;
- ASSERT_EQ(0U, loc.getStart());
- ASSERT_EQ(5U, loc.getEnd());
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.peek(reader, token, data));
+ expectData("test1", 0, 5, 0, 5, token, data);
ASSERT_EQ(0U, reader.getOffset());
ASSERT_EQ(5U, reader.getPeekOffset());
}
{
Token token;
- ASSERT_TRUE(tokenizer.peek(reader, token));
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.peek(reader, token, data));
ASSERT_EQ(tid, token.id);
ASSERT_EQ(":", token.content);
@@ -261,35 +303,26 @@ TEST(Tokenizer, simplePeekToken)
{
Token token;
- ASSERT_TRUE(tokenizer.peek(reader, token));
-
- ASSERT_EQ(Tokens::Data, token.id);
- ASSERT_EQ("test2", token.content);
-
- SourceLocation loc = token.location;
- ASSERT_EQ(6U, loc.getStart());
- ASSERT_EQ(11U, loc.getEnd());
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.peek(reader, token, data));
+ expectData("test2", 6, 11, 6, 11, token, data);
ASSERT_EQ(0U, reader.getOffset());
ASSERT_EQ(11U, reader.getPeekOffset());
}
{
Token token;
- ASSERT_TRUE(tokenizer.read(reader, token));
-
- ASSERT_EQ(Tokens::Data, token.id);
- ASSERT_EQ("test1", token.content);
-
- SourceLocation loc = token.location;
- ASSERT_EQ(0U, loc.getStart());
- ASSERT_EQ(5U, loc.getEnd());
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
+ expectData("test1", 0, 5, 0, 5, token, data);
ASSERT_EQ(5U, reader.getOffset());
ASSERT_EQ(5U, reader.getPeekOffset());
}
{
Token token;
- ASSERT_TRUE(tokenizer.read(reader, token));
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
ASSERT_EQ(tid, token.id);
ASSERT_EQ(":", token.content);
@@ -303,14 +336,9 @@ TEST(Tokenizer, simplePeekToken)
{
Token token;
- ASSERT_TRUE(tokenizer.read(reader, token));
-
- ASSERT_EQ(Tokens::Data, token.id);
- ASSERT_EQ("test2", token.content);
-
- SourceLocation loc = token.location;
- ASSERT_EQ(6U, loc.getStart());
- ASSERT_EQ(11U, loc.getEnd());
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
+ expectData("test2", 6, 11, 6, 11, token, data);
ASSERT_EQ(11U, reader.getOffset());
ASSERT_EQ(11U, reader.getPeekOffset());
}
@@ -320,6 +348,7 @@ TEST(Tokenizer, ambiguousTokens)
{
CharReader reader{"abc"};
Tokenizer tokenizer;
+ TokenizedData data;
TokenId t1 = tokenizer.registerToken("abd");
TokenId t2 = tokenizer.registerToken("bc");
@@ -328,16 +357,17 @@ TEST(Tokenizer, ambiguousTokens)
ASSERT_EQ(1U, t2);
Token token;
- ASSERT_TRUE(tokenizer.read(reader, token));
+ data.clear();
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
- ASSERT_EQ(Tokens::Data, token.id);
- ASSERT_EQ("a", token.content);
+ expectData("a", 0, 1, 0, 1, token, data);
SourceLocation loc = token.location;
ASSERT_EQ(0U, loc.getStart());
ASSERT_EQ(1U, loc.getEnd());
- ASSERT_TRUE(tokenizer.read(reader, token));
+ data.clear();
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
ASSERT_EQ(t2, token.id);
ASSERT_EQ("bc", token.content);
@@ -346,7 +376,8 @@ TEST(Tokenizer, ambiguousTokens)
ASSERT_EQ(1U, loc.getStart());
ASSERT_EQ(3U, loc.getEnd());
- ASSERT_FALSE(tokenizer.read(reader, token));
+ data.clear();
+ ASSERT_FALSE(tokenizer.read(reader, token, data));
}
TEST(Tokenizer, commentTestWhitespacePreserve)
@@ -354,7 +385,7 @@ TEST(Tokenizer, commentTestWhitespacePreserve)
CharReader reader{"Test/Test /* Block Comment */", 0};
// 012345678901234567890123456789
// 0 1 2
- Tokenizer tokenizer(WhitespaceMode::PRESERVE);
+ Tokenizer tokenizer;
const TokenId t1 = tokenizer.registerToken("/");
const TokenId t2 = tokenizer.registerToken("/*");
@@ -370,45 +401,189 @@ TEST(Tokenizer, commentTestWhitespacePreserve)
Token t;
for (auto &te : expected) {
- EXPECT_TRUE(tokenizer.read(reader, t));
+ TokenizedData data(0);
+ EXPECT_TRUE(tokenizer.read(reader, t, data));
EXPECT_EQ(te.id, t.id);
- EXPECT_EQ(te.content, t.content);
+ if (te.id != Tokens::Data) {
+ EXPECT_EQ(te.content, t.content);
+ } else {
+ TokenizedDataReader dataReader = data.reader();
+ Token textToken;
+ ASSERT_TRUE(dataReader.read(textToken, TokenSet{},
+ WhitespaceMode::PRESERVE));
+ EXPECT_TRUE(dataReader.atEnd());
+ EXPECT_EQ(te.content, textToken.content);
+ }
EXPECT_EQ(te.location.getSourceId(), t.location.getSourceId());
EXPECT_EQ(te.location.getStart(), t.location.getStart());
EXPECT_EQ(te.location.getEnd(), t.location.getEnd());
}
- ASSERT_FALSE(tokenizer.read(reader, t));
+
+ TokenizedData data;
+ ASSERT_FALSE(tokenizer.read(reader, t, data));
}
-TEST(Tokenizer, commentTestWhitespaceCollapse)
+TEST(Tokenizer, nonPrimaryTokens)
{
- CharReader reader{"Test/Test /* Block Comment */", 0};
- // 012345678901234567890123456789
- // 0 1 2
- Tokenizer tokenizer(WhitespaceMode::COLLAPSE);
+ CharReader reader{
+ "<<switch to $inline \\math mode$ they said, see the world they "
+ "said>>"};
+ // 012345678901234567890 12345678901234567890123456789012345678901234567
+ // 0 1 2 3 4 5 6
- const TokenId t1 = tokenizer.registerToken("/");
- const TokenId t2 = tokenizer.registerToken("/*");
- const TokenId t3 = tokenizer.registerToken("*/");
+ Tokenizer tokenizer;
- std::vector<Token> expected = {
- {Tokens::Data, "Test", SourceLocation{0, 0, 4}},
- {t1, "/", SourceLocation{0, 4, 5}},
- {Tokens::Data, "Test", SourceLocation{0, 5, 9}},
- {t2, "/*", SourceLocation{0, 10, 12}},
- {Tokens::Data, "Block Comment", SourceLocation{0, 13, 26}},
- {t3, "*/", SourceLocation{0, 27, 29}}};
+ TokenId tBackslash = tokenizer.registerToken("\\");
+ TokenId tDollar = tokenizer.registerToken("$", false);
+ TokenId tSpeechStart = tokenizer.registerToken("<<", false);
+ TokenId tSpeechEnd = tokenizer.registerToken(">>", false);
- Token t;
- for (auto &te : expected) {
- EXPECT_TRUE(tokenizer.read(reader, t));
- EXPECT_EQ(te.id, t.id);
- EXPECT_EQ(te.content, t.content);
- EXPECT_EQ(te.location.getSourceId(), t.location.getSourceId());
- EXPECT_EQ(te.location.getStart(), t.location.getStart());
- EXPECT_EQ(te.location.getEnd(), t.location.getEnd());
+ TokenSet tokens = TokenSet{tDollar, tSpeechStart, tSpeechEnd};
+
+ Token token, textToken;
+ {
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
+ ASSERT_EQ(Tokens::Data, token.id);
+
+ TokenizedDataReader dataReader = data.reader();
+ assertToken(dataReader, tSpeechStart, "<<", tokens,
+ WhitespaceMode::TRIM, 0, 2);
+ assertText(dataReader, "switch to", tokens, WhitespaceMode::TRIM, 2,
+ 11);
+ assertToken(dataReader, tDollar, "$", tokens, WhitespaceMode::TRIM, 12,
+ 13);
+ assertText(dataReader, "inline", tokens, WhitespaceMode::TRIM, 13, 19);
+ assertEnd(dataReader);
+ }
+
+ {
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
+ ASSERT_EQ(tBackslash, token.id);
+ ASSERT_EQ(20U, token.location.getStart());
+ ASSERT_EQ(21U, token.location.getEnd());
+ }
+
+ {
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
+ ASSERT_EQ(Tokens::Data, token.id);
+
+ TokenizedDataReader dataReader = data.reader();
+ assertText(dataReader, "math mode", tokens, WhitespaceMode::TRIM, 21,
+ 30);
+ assertToken(dataReader, tDollar, "$", tokens, WhitespaceMode::TRIM, 30,
+ 31);
+ assertText(dataReader, "they said, see the world they said", tokens,
+ WhitespaceMode::TRIM, 32, 66);
+ assertToken(dataReader, tSpeechEnd, ">>", tokens, WhitespaceMode::TRIM,
+ 66, 68);
+ assertEnd(dataReader);
+ }
+
+ TokenizedData data;
+ ASSERT_FALSE(tokenizer.read(reader, token, data));
+}
+
+TEST(Tokenizer, primaryNonPrimaryTokenInteraction)
+{
+ CharReader reader{"<<test1>><test2><<test3\\><<<test4>>>"};
+ // 01234567890123456789012 3456789012345
+ // 0 1 2 3
+
+ Tokenizer tokenizer;
+
+ TokenId tP1 = tokenizer.registerToken("<", true);
+ TokenId tP2 = tokenizer.registerToken(">", true);
+ TokenId tP3 = tokenizer.registerToken("\\>", true);
+ TokenId tN1 = tokenizer.registerToken("<<", false);
+ TokenId tN2 = tokenizer.registerToken(">>", false);
+
+ TokenSet tokens = TokenSet{tN1, tN2};
+
+ Token token, textToken;
+ {
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
+ ASSERT_EQ(Tokens::Data, token.id);
+
+ TokenizedDataReader dataReader = data.reader();
+ assertToken(dataReader, tN1, "<<", tokens, WhitespaceMode::TRIM, 0, 2);
+ assertText(dataReader, "test1", tokens, WhitespaceMode::TRIM, 2, 7);
+ assertToken(dataReader, tN2, ">>", tokens, WhitespaceMode::TRIM, 7, 9);
+ assertEnd(dataReader);
+ }
+
+ assertPrimaryToken(reader, tokenizer, tP1, "<", 9, 10);
+ assertDataToken(reader, tokenizer, "test2", 10, 15, 10, 15);
+ assertPrimaryToken(reader, tokenizer, tP2, ">", 15, 16);
+
+ {
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
+ ASSERT_EQ(Tokens::Data, token.id);
+
+ TokenizedDataReader dataReader = data.reader();
+ assertToken(dataReader, tN1, "<<", tokens, WhitespaceMode::TRIM, 16, 18);
+ assertText(dataReader, "test3", tokens, WhitespaceMode::TRIM, 18, 23);
+ assertEnd(dataReader);
+ }
+
+ assertPrimaryToken(reader, tokenizer, tP3, "\\>", 23, 25);
+
+ {
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
+ ASSERT_EQ(Tokens::Data, token.id);
+
+ TokenizedDataReader dataReader = data.reader();
+ assertToken(dataReader, tN1, "<<", tokens, WhitespaceMode::TRIM, 25, 27);
+ assertEnd(dataReader);
+ }
+
+ assertPrimaryToken(reader, tokenizer, tP1, "<", 27, 28);
+
+ {
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
+ ASSERT_EQ(Tokens::Data, token.id);
+
+ TokenizedDataReader dataReader = data.reader();
+ assertText(dataReader, "test4", tokens, WhitespaceMode::TRIM, 28, 33);
+ assertToken(dataReader, tN2, ">>", tokens, WhitespaceMode::TRIM, 33, 35);
+ assertEnd(dataReader);
+ }
+
+ assertPrimaryToken(reader, tokenizer, tP2, ">", 35, 36);
+
+ TokenizedData data;
+ ASSERT_FALSE(tokenizer.read(reader, token, data));
+}
+
+TEST(Tokenizer, ambiguousTokens2)
+{
+ CharReader reader{"<\\"};
+
+ Tokenizer tokenizer;
+
+ TokenId tBackslash = tokenizer.registerToken("\\");
+ TokenId tAnnotationStart = tokenizer.registerToken("<\\");
+
+ TokenSet tokens = TokenSet{tBackslash, tAnnotationStart};
+ Token token;
+ {
+ TokenizedData data;
+ ASSERT_TRUE(tokenizer.read(reader, token, data));
+ ASSERT_EQ("<\\", token.content);
+ ASSERT_EQ(tAnnotationStart, token.id);
+ ASSERT_TRUE(data.empty());
+ }
+
+ {
+ TokenizedData data;
+ ASSERT_FALSE(tokenizer.read(reader, token, data));
}
- ASSERT_FALSE(tokenizer.read(reader, t));
}
}
diff --git a/test/formats/osml/OsmlStreamParserTest.cpp b/test/formats/osml/OsmlStreamParserTest.cpp
index d52fa5b..d47f529 100644
--- a/test/formats/osml/OsmlStreamParserTest.cpp
+++ b/test/formats/osml/OsmlStreamParserTest.cpp
@@ -21,143 +21,205 @@
#include <iostream>
#include <core/common/CharReader.hpp>
+#include <core/common/Variant.hpp>
#include <core/frontend/TerminalLogger.hpp>
-
+#include <core/parser/utils/TokenizedData.hpp>
#include <formats/osml/OsmlStreamParser.hpp>
+#include <core/parser/utils/TokenizedDataTestUtils.hpp>
+
namespace ousia {
static TerminalLogger logger(std::cerr, true);
// static ConcreteLogger logger;
-static void assertCommand(OsmlStreamParser &reader, const std::string &name,
- SourceOffset start = InvalidSourceOffset,
- SourceOffset end = InvalidSourceOffset)
+static void assertCommandStart(OsmlStreamParser &parser,
+ const std::string &name, bool rangeCommand,
+ SourceOffset start = InvalidSourceOffset,
+ SourceOffset end = InvalidSourceOffset)
{
- ASSERT_EQ(OsmlStreamParser::State::COMMAND, reader.parse());
- EXPECT_EQ(name, reader.getCommandName().asString());
+ ASSERT_EQ(OsmlStreamParser::State::COMMAND_START, parser.parse());
+ EXPECT_EQ(name, parser.getCommandName().asString());
+ EXPECT_EQ(rangeCommand, parser.inRangeCommand());
if (start != InvalidSourceOffset) {
- EXPECT_EQ(start, reader.getCommandName().getLocation().getStart());
- EXPECT_EQ(start, reader.getLocation().getStart());
+ EXPECT_EQ(start, parser.getCommandName().getLocation().getStart());
+ EXPECT_EQ(start, parser.getLocation().getStart());
}
if (end != InvalidSourceOffset) {
- EXPECT_EQ(end, reader.getCommandName().getLocation().getEnd());
- EXPECT_EQ(end, reader.getLocation().getEnd());
+ EXPECT_EQ(end, parser.getCommandName().getLocation().getEnd());
+ EXPECT_EQ(end, parser.getLocation().getEnd());
}
}
-static void assertCommand(OsmlStreamParser &reader, const std::string &name,
- const Variant::mapType &args,
+static void assertCommandStart(OsmlStreamParser &parser,
+ const std::string &name, bool rangeCommand,
+ const Variant::mapType &args,
+ SourceOffset start = InvalidSourceOffset,
+ SourceOffset end = InvalidSourceOffset)
+{
+ assertCommandStart(parser, name, rangeCommand, start, end);
+ EXPECT_EQ(args, parser.getCommandArguments());
+}
+
+static void assertCommand(OsmlStreamParser &parser, const std::string &name,
SourceOffset start = InvalidSourceOffset,
SourceOffset end = InvalidSourceOffset)
{
- assertCommand(reader, name, start, end);
- EXPECT_EQ(args, reader.getCommandArguments());
+ assertCommandStart(parser, name, false, Variant::mapType{}, start, end);
}
-static void assertData(OsmlStreamParser &reader, const std::string &data,
- SourceOffset start = InvalidSourceOffset,
- SourceOffset end = InvalidSourceOffset)
+static void assertRangeEnd(OsmlStreamParser &parser,
+ SourceOffset start = InvalidSourceOffset,
+ SourceOffset end = InvalidSourceOffset)
{
- ASSERT_EQ(OsmlStreamParser::State::DATA, reader.parse());
- EXPECT_EQ(data, reader.getData().asString());
+ ASSERT_EQ(OsmlStreamParser::State::RANGE_END, parser.parse());
if (start != InvalidSourceOffset) {
- EXPECT_EQ(start, reader.getData().getLocation().getStart());
- EXPECT_EQ(start, reader.getLocation().getStart());
+ EXPECT_EQ(start, parser.getLocation().getStart());
}
if (end != InvalidSourceOffset) {
- EXPECT_EQ(end, reader.getData().getLocation().getEnd());
- EXPECT_EQ(end, reader.getLocation().getEnd());
+ EXPECT_EQ(end, parser.getLocation().getEnd());
+ }
+}
+
+static void assertTextData(OsmlStreamParser &parser, const std::string &text,
+ SourceOffset dataStart = InvalidSourceOffset,
+ SourceOffset dataEnd = InvalidSourceOffset,
+ SourceOffset textStart = InvalidSourceOffset,
+ SourceOffset textEnd = InvalidSourceOffset,
+ WhitespaceMode mode = WhitespaceMode::COLLAPSE)
+{
+ ASSERT_EQ(OsmlStreamParser::State::DATA, parser.parse());
+
+ const TokenizedData &data = parser.getData();
+ TokenizedDataReader dataReader = data.reader();
+
+ Token token;
+ ASSERT_TRUE(dataReader.read(token, TokenSet{}, mode));
+ EXPECT_EQ(Tokens::Data, token.id);
+ EXPECT_EQ(text, token.content);
+ if (dataStart != InvalidSourceOffset) {
+ EXPECT_EQ(dataStart, data.getLocation().getStart());
+ EXPECT_EQ(dataStart, parser.getLocation().getStart());
+ }
+ if (dataEnd != InvalidSourceOffset) {
+ EXPECT_EQ(dataEnd, data.getLocation().getEnd());
+ EXPECT_EQ(dataEnd, parser.getLocation().getEnd());
+ }
+ if (textStart != InvalidSourceOffset) {
+ EXPECT_EQ(textStart, token.getLocation().getStart());
+ }
+ if (textEnd != InvalidSourceOffset) {
+ EXPECT_EQ(textEnd, token.getLocation().getEnd());
}
}
-static void assertFieldStart(OsmlStreamParser &reader, bool defaultField,
+static void assertData(OsmlStreamParser &parser, const std::string &text,
+ SourceOffset textStart = InvalidSourceOffset,
+ SourceOffset textEnd = InvalidSourceOffset,
+ WhitespaceMode mode = WhitespaceMode::COLLAPSE)
+{
+ assertTextData(parser, text, InvalidSourceOffset, InvalidSourceOffset,
+ textStart, textEnd, mode);
+}
+
+static void assertEmptyData(OsmlStreamParser &parser)
+{
+ ASSERT_EQ(OsmlStreamParser::State::DATA, parser.parse());
+
+ const TokenizedData &data = parser.getData();
+ TokenizedDataReader dataReader = data.reader();
+
+ Token token;
+ EXPECT_FALSE(dataReader.read(token, TokenSet{}, WhitespaceMode::TRIM));
+}
+
+static void assertFieldStart(OsmlStreamParser &parser, bool defaultField,
SourceOffset start = InvalidSourceOffset,
SourceOffset end = InvalidSourceOffset)
{
- ASSERT_EQ(OsmlStreamParser::State::FIELD_START, reader.parse());
- EXPECT_EQ(defaultField, reader.inDefaultField());
+ ASSERT_EQ(OsmlStreamParser::State::FIELD_START, parser.parse());
+ EXPECT_EQ(defaultField, parser.inDefaultField());
if (start != InvalidSourceOffset) {
- EXPECT_EQ(start, reader.getLocation().getStart());
+ EXPECT_EQ(start, parser.getLocation().getStart());
}
if (end != InvalidSourceOffset) {
- EXPECT_EQ(end, reader.getLocation().getEnd());
+ EXPECT_EQ(end, parser.getLocation().getEnd());
}
}
-static void assertFieldEnd(OsmlStreamParser &reader,
+static void assertFieldEnd(OsmlStreamParser &parser,
SourceOffset start = InvalidSourceOffset,
SourceOffset end = InvalidSourceOffset)
{
- ASSERT_EQ(OsmlStreamParser::State::FIELD_END, reader.parse());
+ ASSERT_EQ(OsmlStreamParser::State::FIELD_END, parser.parse());
if (start != InvalidSourceOffset) {
- EXPECT_EQ(start, reader.getLocation().getStart());
+ EXPECT_EQ(start, parser.getLocation().getStart());
}
if (end != InvalidSourceOffset) {
- EXPECT_EQ(end, reader.getLocation().getEnd());
+ EXPECT_EQ(end, parser.getLocation().getEnd());
}
}
-static void assertAnnotationStart(OsmlStreamParser &reader,
+static void assertAnnotationStart(OsmlStreamParser &parser,
const std::string &name,
SourceOffset start = InvalidSourceOffset,
SourceOffset end = InvalidSourceOffset)
{
- ASSERT_EQ(OsmlStreamParser::State::ANNOTATION_START, reader.parse());
- EXPECT_EQ(name, reader.getCommandName().asString());
+ ASSERT_EQ(OsmlStreamParser::State::ANNOTATION_START, parser.parse());
+ EXPECT_EQ(name, parser.getCommandName().asString());
if (start != InvalidSourceOffset) {
- EXPECT_EQ(start, reader.getCommandName().getLocation().getStart());
- EXPECT_EQ(start, reader.getLocation().getStart());
+ EXPECT_EQ(start, parser.getCommandName().getLocation().getStart());
+ EXPECT_EQ(start, parser.getLocation().getStart());
}
if (end != InvalidSourceOffset) {
- EXPECT_EQ(end, reader.getCommandName().getLocation().getEnd());
- EXPECT_EQ(end, reader.getLocation().getEnd());
+ EXPECT_EQ(end, parser.getCommandName().getLocation().getEnd());
+ EXPECT_EQ(end, parser.getLocation().getEnd());
}
}
-static void assertAnnotationStart(OsmlStreamParser &reader,
+static void assertAnnotationStart(OsmlStreamParser &parser,
const std::string &name,
const Variant::mapType &args,
SourceOffset start = InvalidSourceOffset,
SourceOffset end = InvalidSourceOffset)
{
- assertAnnotationStart(reader, name, start, end);
- EXPECT_EQ(args, reader.getCommandArguments());
+ assertAnnotationStart(parser, name, start, end);
+ EXPECT_EQ(args, parser.getCommandArguments());
}
-static void assertAnnotationEnd(OsmlStreamParser &reader,
+static void assertAnnotationEnd(OsmlStreamParser &parser,
const std::string &name,
const std::string &elementName,
SourceOffset start = InvalidSourceOffset,
SourceOffset end = InvalidSourceOffset)
{
- ASSERT_EQ(OsmlStreamParser::State::ANNOTATION_END, reader.parse());
- ASSERT_EQ(name, reader.getCommandName().asString());
+ ASSERT_EQ(OsmlStreamParser::State::ANNOTATION_END, parser.parse());
+ ASSERT_EQ(name, parser.getCommandName().asString());
if (!elementName.empty()) {
- ASSERT_EQ(1U, reader.getCommandArguments().asMap().size());
- ASSERT_EQ(1U, reader.getCommandArguments().asMap().count("name"));
+ ASSERT_EQ(1U, parser.getCommandArguments().asMap().size());
+ ASSERT_EQ(1U, parser.getCommandArguments().asMap().count("name"));
- auto it = reader.getCommandArguments().asMap().find("name");
+ auto it = parser.getCommandArguments().asMap().find("name");
ASSERT_EQ(elementName, it->second.asString());
}
if (start != InvalidSourceOffset) {
- EXPECT_EQ(start, reader.getLocation().getStart());
+ EXPECT_EQ(start, parser.getLocation().getStart());
}
if (end != InvalidSourceOffset) {
- EXPECT_EQ(end, reader.getLocation().getEnd());
+ EXPECT_EQ(end, parser.getLocation().getEnd());
}
}
-static void assertEnd(OsmlStreamParser &reader,
+static void assertEnd(OsmlStreamParser &parser,
SourceOffset start = InvalidSourceOffset,
SourceOffset end = InvalidSourceOffset)
{
- ASSERT_EQ(OsmlStreamParser::State::END, reader.parse());
+ ASSERT_EQ(OsmlStreamParser::State::END, parser.parse());
if (start != InvalidSourceOffset) {
- EXPECT_EQ(start, reader.getLocation().getStart());
+ EXPECT_EQ(start, parser.getLocation().getStart());
}
if (end != InvalidSourceOffset) {
- EXPECT_EQ(end, reader.getLocation().getEnd());
+ EXPECT_EQ(end, parser.getLocation().getEnd());
}
}
@@ -166,9 +228,9 @@ TEST(OsmlStreamParser, empty)
const char *testString = "";
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- ASSERT_EQ(OsmlStreamParser::State::END, reader.parse());
+ assertEnd(parser, 0, 0);
}
TEST(OsmlStreamParser, oneCharacter)
@@ -176,57 +238,102 @@ TEST(OsmlStreamParser, oneCharacter)
const char *testString = "a";
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertData(reader, "a", 0, 1);
+ assertTextData(parser, "a", 0, 1, 0, 1, WhitespaceMode::COLLAPSE);
+ assertEnd(parser, 1, 1);
}
-TEST(OsmlStreamParser, whitespaceElimination)
+TEST(OsmlStreamParser, whitespacePreserve)
{
const char *testString = " hello \t world ";
// 0123456 78901234
// 0 1
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertData(reader, "hello world", 1, 14);
+ assertTextData(parser, " hello \t world ", 0, 15, 0, 15,
+ WhitespaceMode::PRESERVE);
+ assertEnd(parser, 15, 15);
}
-TEST(OsmlStreamParser, whitespaceEliminationWithLinebreak)
+TEST(OsmlStreamParser, whitespaceTrim)
+{
+ const char *testString = " hello \t world ";
+ // 0123456 78901234
+ // 0 1
+ CharReader charReader(testString);
+
+ OsmlStreamParser parser(charReader, logger);
+
+ assertTextData(parser, "hello \t world", 0, 15, 1, 14,
+ WhitespaceMode::TRIM);
+ assertEnd(parser, 15, 15);
+}
+
+TEST(OsmlStreamParser, whitespaceCollapse)
+{
+ const char *testString = " hello \t world ";
+ // 0123456 78901234
+ // 0 1
+ CharReader charReader(testString);
+
+ OsmlStreamParser parser(charReader, logger);
+
+ assertTextData(parser, "hello world", 0, 15, 1, 14,
+ WhitespaceMode::COLLAPSE);
+ assertEnd(parser, 15, 15);
+}
+
+TEST(OsmlStreamParser, whitespaceCollapseLinebreak)
{
const char *testString = " hello \n world ";
// 0123456 78901234
// 0 1
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertData(reader, "hello world", 1, 14);
+ assertTextData(parser, "hello world", 0, 15, 1, 14,
+ WhitespaceMode::COLLAPSE);
+ assertEnd(parser, 15, 15);
}
-TEST(OsmlStreamParser, escapeWhitespace)
+TEST(OsmlStreamParser, whitespaceCollapseProtected)
{
const char *testString = " hello\\ \\ world ";
// 012345 67 89012345
// 0 1
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertData(reader, "hello world", 1, 15);
+ assertTextData(parser, "hello world", 0, 16, 1, 15,
+ WhitespaceMode::COLLAPSE);
+ assertEnd(parser, 16, 16);
+}
+
+TEST(OsmlStreamParser, whitespaceCollapseProtected2)
+{
+ const char *testString = " hello \\ \\ world ";
+ // 012345 67 89012345
+ // 0 1
+ CharReader charReader(testString);
+
+ OsmlStreamParser parser(charReader, logger);
+
+ assertTextData(parser, "hello world", 0, 17, 1, 16,
+ WhitespaceMode::COLLAPSE);
+ assertEnd(parser, 17, 17);
}
static void testEscapeSpecialCharacter(const std::string &c)
{
CharReader charReader(std::string("\\") + c);
- OsmlStreamParser reader(charReader, logger);
- EXPECT_EQ(OsmlStreamParser::State::DATA, reader.parse());
- EXPECT_EQ(c, reader.getData().asString());
-
- SourceLocation loc = reader.getData().getLocation();
- EXPECT_EQ(0U, loc.getStart());
- EXPECT_EQ(1U + c.size(), loc.getEnd());
+ OsmlStreamParser parser(charReader, logger);
+ assertTextData(parser, c, 0, 2, 0, 2, WhitespaceMode::PRESERVE);
+ assertEnd(parser, 2, 2);
}
TEST(OsmlStreamParser, escapeSpecialCharacters)
@@ -239,9 +346,11 @@ TEST(OsmlStreamParser, escapeSpecialCharacters)
TEST(OsmlStreamParser, simpleSingleLineComment)
{
const char *testString = "% This is a single line comment";
+ // 0123456789012345678901234567890
+ // 0 1 2 3
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
- ASSERT_EQ(OsmlStreamParser::State::END, reader.parse());
+ OsmlStreamParser parser(charReader, logger);
+ assertEnd(parser, 31, 31);
}
TEST(OsmlStreamParser, singleLineComment)
@@ -250,24 +359,10 @@ TEST(OsmlStreamParser, singleLineComment)
// 01234567890123456789012345678901 23
// 0 1 2 3
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
- {
- ASSERT_EQ(OsmlStreamParser::State::DATA, reader.parse());
- ASSERT_EQ("a", reader.getData().asString());
- SourceLocation loc = reader.getData().getLocation();
- ASSERT_EQ(0U, loc.getStart());
- ASSERT_EQ(1U, loc.getEnd());
- }
-
- {
- ASSERT_EQ(OsmlStreamParser::State::DATA, reader.parse());
- ASSERT_EQ("b", reader.getData().asString());
- SourceLocation loc = reader.getData().getLocation();
- ASSERT_EQ(33U, loc.getStart());
- ASSERT_EQ(34U, loc.getEnd());
- }
+ OsmlStreamParser parser(charReader, logger);
- ASSERT_EQ(OsmlStreamParser::State::END, reader.parse());
+ assertTextData(parser, "ab", 0, 34, 0, 34, WhitespaceMode::PRESERVE);
+ assertEnd(parser, 34, 34);
}
TEST(OsmlStreamParser, multilineComment)
@@ -276,24 +371,26 @@ TEST(OsmlStreamParser, multilineComment)
// 0123456789012 3 456789012345678901234567890
// 0 1 2 3 4
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
- {
- ASSERT_EQ(OsmlStreamParser::State::DATA, reader.parse());
- ASSERT_EQ("a", reader.getData().asString());
- SourceLocation loc = reader.getData().getLocation();
- ASSERT_EQ(0U, loc.getStart());
- ASSERT_EQ(1U, loc.getEnd());
- }
+ OsmlStreamParser parser(charReader, logger);
- {
- ASSERT_EQ(OsmlStreamParser::State::DATA, reader.parse());
- ASSERT_EQ("b", reader.getData().asString());
- SourceLocation loc = reader.getData().getLocation();
- ASSERT_EQ(40U, loc.getStart());
- ASSERT_EQ(41U, loc.getEnd());
- }
+ assertTextData(parser, "ab", 0, 41, 0, 41, WhitespaceMode::PRESERVE);
+ assertEnd(parser, 41, 41);
+}
- ASSERT_EQ(OsmlStreamParser::State::END, reader.parse());
+TEST(OsmlStreamParser, unfinishedMultilineComment)
+{
+ const char *testString = "a%{ This is a\n\n multiline line comment";
+ // 0123456789012 3 456789012345678901234567
+ // 0 1 2 3
+ CharReader charReader(testString);
+ OsmlStreamParser parser(charReader, logger);
+
+ logger.reset();
+
+ ASSERT_FALSE(logger.hasError());
+ assertTextData(parser, "a", 0, 1, 0, 1, WhitespaceMode::PRESERVE);
+ ASSERT_TRUE(logger.hasError());
+ assertEnd(parser, 38, 38);
}
TEST(OsmlStreamParser, nestedMultilineComment)
@@ -302,24 +399,10 @@ TEST(OsmlStreamParser, nestedMultilineComment)
// 0123456789012 3 456789012345678901234567890
// 0 1 2 3 4
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
- {
- ASSERT_EQ(OsmlStreamParser::State::DATA, reader.parse());
- ASSERT_EQ("a", reader.getData().asString());
- SourceLocation loc = reader.getData().getLocation();
- ASSERT_EQ(0U, loc.getStart());
- ASSERT_EQ(1U, loc.getEnd());
- }
+ OsmlStreamParser parser(charReader, logger);
- {
- ASSERT_EQ(OsmlStreamParser::State::DATA, reader.parse());
- ASSERT_EQ("b", reader.getData().asString());
- SourceLocation loc = reader.getData().getLocation();
- ASSERT_EQ(40U, loc.getStart());
- ASSERT_EQ(41U, loc.getEnd());
- }
-
- ASSERT_EQ(OsmlStreamParser::State::END, reader.parse());
+ assertTextData(parser, "ab", 0, 41, 0, 41, WhitespaceMode::PRESERVE);
+ assertEnd(parser, 41, 41);
}
TEST(OsmlStreamParser, simpleCommand)
@@ -327,45 +410,27 @@ TEST(OsmlStreamParser, simpleCommand)
const char *testString = "\\test";
// 0 12345
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
- ASSERT_EQ(OsmlStreamParser::State::COMMAND, reader.parse());
-
- Variant commandName = reader.getCommandName();
- ASSERT_EQ("test", commandName.asString());
+ OsmlStreamParser parser(charReader, logger);
- SourceLocation loc = commandName.getLocation();
- ASSERT_EQ(0U, loc.getStart());
- ASSERT_EQ(5U, loc.getEnd());
-
- ASSERT_EQ(0U, reader.getCommandArguments().asMap().size());
- ASSERT_EQ(OsmlStreamParser::State::END, reader.parse());
+ assertCommand(parser, "test", 0, 5);
+ assertEnd(parser);
}
TEST(OsmlStreamParser, simpleCommandWithName)
{
- const char *testString = "\\test#bla";
- // 0 12345678
+ const char *testString = "\\test#foo";
+ // 012345678
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
- ASSERT_EQ(OsmlStreamParser::State::COMMAND, reader.parse());
-
- Variant commandName = reader.getCommandName();
- ASSERT_EQ("test", commandName.asString());
- SourceLocation loc = commandName.getLocation();
- ASSERT_EQ(0U, loc.getStart());
- ASSERT_EQ(5U, loc.getEnd());
+ OsmlStreamParser parser(charReader, logger);
- Variant commandArguments = reader.getCommandArguments();
- ASSERT_TRUE(commandArguments.isMap());
- ASSERT_EQ(1U, commandArguments.asMap().size());
- ASSERT_EQ(1U, commandArguments.asMap().count("name"));
- ASSERT_EQ("bla", commandArguments.asMap()["name"].asString());
+ assertCommandStart(parser, "test", false, Variant::mapType{{"name", "foo"}},
+ 0, 5);
- loc = commandArguments.asMap()["name"].getLocation();
- ASSERT_EQ(5U, loc.getStart());
- ASSERT_EQ(9U, loc.getEnd());
+ Variant::mapType args = parser.getCommandArguments().asMap();
+ ASSERT_EQ(5U, args["name"].getLocation().getStart());
+ ASSERT_EQ(9U, args["name"].getLocation().getEnd());
- ASSERT_EQ(OsmlStreamParser::State::END, reader.parse());
+ assertEnd(parser);
}
TEST(OsmlStreamParser, simpleCommandWithArguments)
@@ -374,38 +439,21 @@ TEST(OsmlStreamParser, simpleCommandWithArguments)
// 0 123456789012345 678901 2
// 0 1 2
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
- ASSERT_EQ(OsmlStreamParser::State::COMMAND, reader.parse());
-
- Variant commandName = reader.getCommandName();
- ASSERT_EQ("test", commandName.asString());
- SourceLocation loc = commandName.getLocation();
- ASSERT_EQ(0U, loc.getStart());
- ASSERT_EQ(5U, loc.getEnd());
-
- Variant commandArguments = reader.getCommandArguments();
- ASSERT_TRUE(commandArguments.isMap());
- ASSERT_EQ(3U, commandArguments.asMap().size());
- ASSERT_EQ(1U, commandArguments.asMap().count("a"));
- ASSERT_EQ(1U, commandArguments.asMap().count("b"));
- ASSERT_EQ(1U, commandArguments.asMap().count("c"));
- ASSERT_EQ(1, commandArguments.asMap()["a"].asInt());
- ASSERT_EQ(2, commandArguments.asMap()["b"].asInt());
- ASSERT_EQ("test", commandArguments.asMap()["c"].asString());
-
- loc = commandArguments.asMap()["a"].getLocation();
- ASSERT_EQ(8U, loc.getStart());
- ASSERT_EQ(9U, loc.getEnd());
+ OsmlStreamParser parser(charReader, logger);
- loc = commandArguments.asMap()["b"].getLocation();
- ASSERT_EQ(12U, loc.getStart());
- ASSERT_EQ(13U, loc.getEnd());
+ assertCommandStart(parser, "test", false,
+ Variant::mapType{{"a", 1}, {"b", 2}, {"c", "test"}}, 0,
+ 5);
- loc = commandArguments.asMap()["c"].getLocation();
- ASSERT_EQ(16U, loc.getStart());
- ASSERT_EQ(22U, loc.getEnd());
+ Variant::mapType args = parser.getCommandArguments().asMap();
+ ASSERT_EQ(8U, args["a"].getLocation().getStart());
+ ASSERT_EQ(9U, args["a"].getLocation().getEnd());
+ ASSERT_EQ(12U, args["b"].getLocation().getStart());
+ ASSERT_EQ(13U, args["b"].getLocation().getEnd());
+ ASSERT_EQ(16U, args["c"].getLocation().getStart());
+ ASSERT_EQ(22U, args["c"].getLocation().getEnd());
- ASSERT_EQ(OsmlStreamParser::State::END, reader.parse());
+ assertEnd(parser);
}
TEST(OsmlStreamParser, simpleCommandWithArgumentsAndName)
@@ -414,44 +462,24 @@ TEST(OsmlStreamParser, simpleCommandWithArgumentsAndName)
// 0 1234567890123456789 01234 56
// 0 1 2
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
- ASSERT_EQ(OsmlStreamParser::State::COMMAND, reader.parse());
+ OsmlStreamParser parser(charReader, logger);
- Variant commandName = reader.getCommandName();
- ASSERT_EQ("test", commandName.asString());
- SourceLocation loc = commandName.getLocation();
- ASSERT_EQ(0U, loc.getStart());
- ASSERT_EQ(5U, loc.getEnd());
+ assertCommandStart(
+ parser, "test", false,
+ Variant::mapType{{"name", "bla"}, {"a", 1}, {"b", 2}, {"c", "test"}}, 0,
+ 5);
- Variant commandArguments = reader.getCommandArguments();
- ASSERT_TRUE(commandArguments.isMap());
- ASSERT_EQ(4U, commandArguments.asMap().size());
- ASSERT_EQ(1U, commandArguments.asMap().count("a"));
- ASSERT_EQ(1U, commandArguments.asMap().count("b"));
- ASSERT_EQ(1U, commandArguments.asMap().count("c"));
- ASSERT_EQ(1U, commandArguments.asMap().count("name"));
- ASSERT_EQ(1, commandArguments.asMap()["a"].asInt());
- ASSERT_EQ(2, commandArguments.asMap()["b"].asInt());
- ASSERT_EQ("test", commandArguments.asMap()["c"].asString());
- ASSERT_EQ("bla", commandArguments.asMap()["name"].asString());
+ Variant::mapType args = parser.getCommandArguments().asMap();
+ ASSERT_EQ(5U, args["name"].getLocation().getStart());
+ ASSERT_EQ(9U, args["name"].getLocation().getEnd());
+ ASSERT_EQ(12U, args["a"].getLocation().getStart());
+ ASSERT_EQ(13U, args["a"].getLocation().getEnd());
+ ASSERT_EQ(16U, args["b"].getLocation().getStart());
+ ASSERT_EQ(17U, args["b"].getLocation().getEnd());
+ ASSERT_EQ(20U, args["c"].getLocation().getStart());
+ ASSERT_EQ(26U, args["c"].getLocation().getEnd());
- loc = commandArguments.asMap()["a"].getLocation();
- ASSERT_EQ(12U, loc.getStart());
- ASSERT_EQ(13U, loc.getEnd());
-
- loc = commandArguments.asMap()["b"].getLocation();
- ASSERT_EQ(16U, loc.getStart());
- ASSERT_EQ(17U, loc.getEnd());
-
- loc = commandArguments.asMap()["c"].getLocation();
- ASSERT_EQ(20U, loc.getStart());
- ASSERT_EQ(26U, loc.getEnd());
-
- loc = commandArguments.asMap()["name"].getLocation();
- ASSERT_EQ(5U, loc.getStart());
- ASSERT_EQ(9U, loc.getEnd());
-
- ASSERT_EQ(OsmlStreamParser::State::END, reader.parse());
+ assertEnd(parser);
}
TEST(OsmlStreamParser, fields)
@@ -460,21 +488,76 @@ TEST(OsmlStreamParser, fields)
// 01234567890123
// 0 1
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
+
+ assertCommand(parser, "test", 0, 5);
+ assertFieldStart(parser, false, 5, 6);
+ assertTextData(parser, "a", 6, 7, 6, 7, WhitespaceMode::PRESERVE);
+ assertFieldEnd(parser, 7, 8);
+
+ assertFieldStart(parser, false, 8, 9);
+ assertTextData(parser, "b", 9, 10, 9, 10, WhitespaceMode::PRESERVE);
+ assertFieldEnd(parser, 10, 11);
+
+ assertFieldStart(parser, false, 11, 12);
+ assertTextData(parser, "c", 12, 13, 12, 13, WhitespaceMode::PRESERVE);
+ assertFieldEnd(parser, 13, 14);
+ assertEnd(parser, 14, 14);
+}
+
+TEST(OsmlStreamParser, fieldsWithoutCommand)
+{
+ const char *testString = "{a}{b}{c}";
+ // 012345678
+ CharReader charReader(testString);
+ OsmlStreamParser parser(charReader, logger);
- assertCommand(reader, "test", 0, 5);
- assertFieldStart(reader, false, 5, 6);
- assertData(reader, "a", 6, 7);
- assertFieldEnd(reader, 7, 8);
+ assertFieldStart(parser, false, 0, 1);
+ assertTextData(parser, "a", 1, 2, 1, 2, WhitespaceMode::PRESERVE);
+ assertFieldEnd(parser, 2, 3);
- assertFieldStart(reader, false, 8, 9);
- assertData(reader, "b", 9, 10);
- assertFieldEnd(reader, 10, 11);
+ assertFieldStart(parser, false, 3, 4);
+ assertTextData(parser, "b", 4, 5, 4, 5, WhitespaceMode::PRESERVE);
+ assertFieldEnd(parser, 5, 6);
- assertFieldStart(reader, false, 11, 12);
- assertData(reader, "c", 12, 13);
- assertFieldEnd(reader, 13, 14);
- assertEnd(reader, 14, 14);
+ assertFieldStart(parser, false, 6, 7);
+ assertTextData(parser, "c", 7, 8, 7, 8, WhitespaceMode::PRESERVE);
+ assertFieldEnd(parser, 8, 9);
+ assertEnd(parser, 9, 9);
+}
+
+TEST(OsmlStreamParser, nestedField)
+{
+ const char *testString = "{{a{b}}}";
+ // 01234567
+ CharReader charReader(testString);
+ OsmlStreamParser parser(charReader, logger);
+
+ assertFieldStart(parser, false, 0, 1);
+ assertFieldStart(parser, false, 1, 2);
+ assertTextData(parser, "a", 2, 3, 2, 3, WhitespaceMode::PRESERVE);
+ assertFieldStart(parser, false, 3, 4);
+ assertTextData(parser, "b", 4, 5, 4, 5, WhitespaceMode::PRESERVE);
+ assertFieldEnd(parser, 5, 6);
+ assertFieldEnd(parser, 6, 7);
+ assertFieldEnd(parser, 7, 8);
+ assertEnd(parser, 8, 8);
+}
+
+TEST(OsmlStreamParser, errorUnbalancedField)
+{
+ const char *testString = "{a";
+ // 01
+ CharReader charReader(testString);
+ OsmlStreamParser parser(charReader, logger);
+
+ logger.reset();
+
+ assertFieldStart(parser, false, 0, 1);
+ assertTextData(parser, "a", 1, 2, 1, 2, WhitespaceMode::PRESERVE);
+ ASSERT_FALSE(logger.hasError());
+ assertEnd(parser, 2, 2);
+ ASSERT_TRUE(logger.hasError());
}
TEST(OsmlStreamParser, dataOutsideField)
@@ -483,19 +566,19 @@ TEST(OsmlStreamParser, dataOutsideField)
// 0123456789012
// 0 1
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertCommand(reader, "test", 0, 5);
- assertFieldStart(reader, false, 5, 6);
- assertData(reader, "a", 6, 7);
- assertFieldEnd(reader, 7, 8);
+ assertCommand(parser, "test", 0, 5);
+ assertFieldStart(parser, false, 5, 6);
+ assertTextData(parser, "a", 6, 7, 6, 7, WhitespaceMode::COLLAPSE);
+ assertFieldEnd(parser, 7, 8);
- assertFieldStart(reader, false, 8, 9);
- assertData(reader, "b", 9, 10);
- assertFieldEnd(reader, 10, 11);
+ assertFieldStart(parser, false, 8, 9);
+ assertTextData(parser, "b", 9, 10, 9, 10, WhitespaceMode::COLLAPSE);
+ assertFieldEnd(parser, 10, 11);
- assertData(reader, "c", 12, 13);
- assertEnd(reader, 13, 13);
+ assertTextData(parser, "c", 11, 13, 12, 13, WhitespaceMode::COLLAPSE);
+ assertEnd(parser, 13, 13);
}
TEST(OsmlStreamParser, nestedCommand)
@@ -504,25 +587,22 @@ TEST(OsmlStreamParser, nestedCommand)
// 012345678 90123456789012
// 0 1 2
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertCommand(reader, "test", 0, 5);
+ assertCommand(parser, "test", 0, 5);
+ assertFieldStart(parser, false, 5, 6);
+ assertData(parser, "a", 6, 7);
+ assertFieldEnd(parser, 7, 8);
- assertFieldStart(reader, false, 5, 6);
- assertData(reader, "a", 6, 7);
- assertFieldEnd(reader, 7, 8);
-
- assertFieldStart(reader, false, 8, 9);
- {
- assertCommand(reader, "test2", 9, 15);
- assertFieldStart(reader, false, 15, 16);
- assertData(reader, "b", 16, 17);
- assertFieldEnd(reader, 17, 18);
- }
- assertData(reader, "c", 19, 20);
- assertFieldEnd(reader, 20, 21);
- assertData(reader, "d", 22, 23);
- assertEnd(reader, 23, 23);
+ assertFieldStart(parser, false, 8, 9);
+ assertCommand(parser, "test2", 9, 15);
+ assertFieldStart(parser, false, 15, 16);
+ assertData(parser, "b", 16, 17);
+ assertFieldEnd(parser, 17, 18);
+ assertData(parser, "c", 19, 20);
+ assertFieldEnd(parser, 20, 21);
+ assertData(parser, "d", 22, 23);
+ assertEnd(parser, 23, 23);
}
TEST(OsmlStreamParser, nestedCommandImmediateEnd)
@@ -531,19 +611,19 @@ TEST(OsmlStreamParser, nestedCommandImmediateEnd)
// 012345 678901234567
// 0 1
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertCommand(reader, "test", 0, 5);
- assertFieldStart(reader, false, 5, 6);
+ assertCommand(parser, "test", 0, 5);
+ assertFieldStart(parser, false, 5, 6);
{
- assertCommand(reader, "test2", 6, 12);
- assertFieldStart(reader, false, 12, 13);
- assertData(reader, "b", 13, 14);
- assertFieldEnd(reader, 14, 15);
+ assertCommand(parser, "test2", 6, 12);
+ assertFieldStart(parser, false, 12, 13);
+ assertData(parser, "b", 13, 14);
+ assertFieldEnd(parser, 14, 15);
}
- assertFieldEnd(reader, 15, 16);
- assertData(reader, "d", 17, 18);
- assertEnd(reader, 18, 18);
+ assertFieldEnd(parser, 15, 16);
+ assertData(parser, "d", 17, 18);
+ assertEnd(parser, 18, 18);
}
TEST(OsmlStreamParser, nestedCommandNoData)
@@ -551,13 +631,13 @@ TEST(OsmlStreamParser, nestedCommandNoData)
const char *testString = "\\test{\\test2}";
// 012345 6789012
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertCommand(reader, "test", 0, 5);
- assertFieldStart(reader, false, 5, 6);
- assertCommand(reader, "test2", 6, 12);
- assertFieldEnd(reader, 12, 13);
- assertEnd(reader, 13, 13);
+ assertCommand(parser, "test", 0, 5);
+ assertFieldStart(parser, false, 5, 6);
+ assertCommand(parser, "test2", 6, 12);
+ assertFieldEnd(parser, 12, 13);
+ assertEnd(parser, 13, 13);
}
TEST(OsmlStreamParser, multipleCommands)
@@ -566,13 +646,16 @@ TEST(OsmlStreamParser, multipleCommands)
// 012 345 678 90
// 0 1
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertCommand(reader, "a", 0, 2);
- assertCommand(reader, "b", 3, 5);
- assertCommand(reader, "c", 6, 8);
- assertCommand(reader, "d", 9, 11);
- assertEnd(reader, 11, 11);
+ assertCommand(parser, "a", 0, 2);
+ assertEmptyData(parser);
+ assertCommand(parser, "b", 3, 5);
+ assertEmptyData(parser);
+ assertCommand(parser, "c", 6, 8);
+ assertEmptyData(parser);
+ assertCommand(parser, "d", 9, 11);
+ assertEnd(parser, 11, 11);
}
TEST(OsmlStreamParser, fieldsWithSpaces)
@@ -581,33 +664,37 @@ TEST(OsmlStreamParser, fieldsWithSpaces)
// 0123 456 789012 3 456 789
// 0 1
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertCommand(reader, "a", 0, 2);
- assertFieldStart(reader, false, 3, 4);
- assertCommand(reader, "b", 4, 6);
- assertCommand(reader, "c", 7, 9);
- assertFieldEnd(reader, 9, 10);
- assertFieldStart(reader, false, 16, 17);
- assertCommand(reader, "d", 17, 19);
- assertFieldEnd(reader, 19, 20);
- assertEnd(reader, 20, 20);
+ assertCommand(parser, "a", 0, 2);
+ assertEmptyData(parser);
+ assertFieldStart(parser, false, 3, 4);
+ assertCommand(parser, "b", 4, 6);
+ assertEmptyData(parser);
+ assertCommand(parser, "c", 7, 9);
+ assertFieldEnd(parser, 9, 10);
+ assertEmptyData(parser);
+ assertFieldStart(parser, false, 16, 17);
+ assertCommand(parser, "d", 17, 19);
+ assertFieldEnd(parser, 19, 20);
+ assertEnd(parser, 20, 20);
}
-TEST(OsmlStreamParser, errorNoFieldToStart)
+TEST(OsmlStreamParser, errorEndButOpenField)
{
const char *testString = "\\a b {";
// 012345
// 0
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
- assertCommand(reader, "a", 0, 2);
- assertData(reader, "b", 3, 4);
+ assertCommand(parser, "a", 0, 2);
+ assertData(parser, "b", 3, 4);
+ assertFieldStart(parser, false, 5, 6);
ASSERT_FALSE(logger.hasError());
- assertEnd(reader, 6, 6);
+ assertEnd(parser, 6, 6);
ASSERT_TRUE(logger.hasError());
}
@@ -618,13 +705,13 @@ TEST(OsmlStreamParser, errorNoFieldToEnd)
// 0
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
- assertCommand(reader, "a", 0, 2);
- assertData(reader, "b", 3, 4);
+ assertCommand(parser, "a", 0, 2);
+ assertData(parser, "b", 3, 4);
ASSERT_FALSE(logger.hasError());
- assertEnd(reader, 6, 6);
+ assertEnd(parser, 6, 6);
ASSERT_TRUE(logger.hasError());
}
@@ -635,17 +722,17 @@ TEST(OsmlStreamParser, errorNoFieldEndNested)
// 0 1
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
- assertCommand(reader, "test", 0, 5);
- assertFieldStart(reader, false, 5, 6);
- assertCommand(reader, "test2", 6, 12);
- assertFieldStart(reader, false, 12, 13);
- assertFieldEnd(reader, 13, 14);
- assertFieldEnd(reader, 14, 15);
+ assertCommand(parser, "test", 0, 5);
+ assertFieldStart(parser, false, 5, 6);
+ assertCommand(parser, "test2", 6, 12);
+ assertFieldStart(parser, false, 12, 13);
+ assertFieldEnd(parser, 13, 14);
+ assertFieldEnd(parser, 14, 15);
ASSERT_FALSE(logger.hasError());
- assertEnd(reader, 16, 16);
+ assertEnd(parser, 16, 16);
ASSERT_TRUE(logger.hasError());
}
@@ -656,18 +743,18 @@ TEST(OsmlStreamParser, errorNoFieldEndNestedData)
// 0 1
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
- assertCommand(reader, "test", 0, 5);
- assertFieldStart(reader, false, 5, 6);
- assertCommand(reader, "test2", 6, 12);
- assertFieldStart(reader, false, 12, 13);
- assertFieldEnd(reader, 13, 14);
- assertFieldEnd(reader, 14, 15);
- assertData(reader, "a", 15, 16);
+ assertCommand(parser, "test", 0, 5);
+ assertFieldStart(parser, false, 5, 6);
+ assertCommand(parser, "test2", 6, 12);
+ assertFieldStart(parser, false, 12, 13);
+ assertFieldEnd(parser, 13, 14);
+ assertFieldEnd(parser, 14, 15);
+ assertData(parser, "a", 15, 16);
ASSERT_FALSE(logger.hasError());
- assertEnd(reader, 17, 17);
+ assertEnd(parser, 17, 17);
ASSERT_TRUE(logger.hasError());
}
@@ -678,12 +765,11 @@ TEST(OsmlStreamParser, beginEnd)
// 0 1 2
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertCommand(reader, "book", 7, 11);
- assertFieldStart(reader, true, 12, 13);
- assertFieldEnd(reader, 17, 21);
- assertEnd(reader, 22, 22);
+ assertCommandStart(parser, "book", true, Variant::mapType{}, 7, 11);
+ assertRangeEnd(parser, 17, 21);
+ assertEnd(parser, 22, 22);
}
TEST(OsmlStreamParser, beginEndWithName)
@@ -693,12 +779,11 @@ TEST(OsmlStreamParser, beginEndWithName)
// 0 1 2
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertCommand(reader, "book", {{"name", "a"}}, 7, 11);
- assertFieldStart(reader, true, 14, 15);
- assertFieldEnd(reader, 19, 23);
- assertEnd(reader, 24, 24);
+ assertCommandStart(parser, "book", true, {{"name", "a"}}, 7, 11);
+ assertRangeEnd(parser, 19, 23);
+ assertEnd(parser, 24, 24);
}
TEST(OsmlStreamParser, beginEndWithNameAndArgs)
@@ -708,13 +793,13 @@ TEST(OsmlStreamParser, beginEndWithNameAndArgs)
// 0 1 2 3 4
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertCommand(reader, "book",
- {{"name", "a"}, {"a", 1}, {"b", 2}, {"c", "test"}}, 7, 11);
- assertFieldStart(reader, true, 32, 33);
- assertFieldEnd(reader, 37, 41);
- assertEnd(reader, 42, 42);
+ assertCommandStart(parser, "book", true,
+ {{"name", "a"}, {"a", 1}, {"b", 2}, {"c", "test"}}, 7,
+ 11);
+ assertRangeEnd(parser, 37, 41);
+ assertEnd(parser, 42, 42);
}
TEST(OsmlStreamParser, beginEndWithNameAndArgsMultipleFields)
@@ -725,23 +810,23 @@ TEST(OsmlStreamParser, beginEndWithNameAndArgsMultipleFields)
// 0 1 2 3 4 5 6
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
-
- assertCommand(reader, "book",
- {{"name", "a"}, {"a", 1}, {"b", 2}, {"c", "test"}}, 7, 11);
- assertFieldStart(reader, false, 32, 33);
- assertData(reader, "a", 33, 34);
- assertCommand(reader, "test", Variant::mapType{}, 35, 40);
- assertFieldEnd(reader, 40, 41);
- assertFieldStart(reader, false, 41, 42);
- assertData(reader, "b", 42, 43);
- assertCommand(reader, "test", Variant::mapType{}, 44, 49);
- assertFieldStart(reader, false, 49, 50);
- assertFieldEnd(reader, 50, 51);
- assertFieldEnd(reader, 51, 52);
- assertFieldStart(reader, true, 52, 53);
- assertFieldEnd(reader, 57, 61);
- assertEnd(reader, 62, 62);
+ OsmlStreamParser parser(charReader, logger);
+
+ assertCommandStart(parser, "book", true,
+ {{"name", "a"}, {"a", 1}, {"b", 2}, {"c", "test"}}, 7,
+ 11);
+ assertFieldStart(parser, false, 32, 33);
+ assertData(parser, "a", 33, 34);
+ assertCommand(parser, "test", 35, 40);
+ assertFieldEnd(parser, 40, 41);
+ assertFieldStart(parser, false, 41, 42);
+ assertData(parser, "b", 42, 43);
+ assertCommand(parser, "test", 44, 49);
+ assertFieldStart(parser, false, 49, 50);
+ assertFieldEnd(parser, 50, 51);
+ assertFieldEnd(parser, 51, 52);
+ assertRangeEnd(parser, 57, 61);
+ assertEnd(parser, 62, 62);
}
TEST(OsmlStreamParser, beginEndWithData)
@@ -751,13 +836,12 @@ TEST(OsmlStreamParser, beginEndWithData)
// 0 1 2
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertCommand(reader, "book", 7, 11);
- assertFieldStart(reader, true, 12, 13);
- assertData(reader, "a", 12, 13);
- assertFieldEnd(reader, 18, 22);
- assertEnd(reader, 23, 23);
+ assertCommandStart(parser, "book", true, Variant::mapType{}, 7, 11);
+ assertData(parser, "a", 12, 13);
+ assertRangeEnd(parser, 18, 22);
+ assertEnd(parser, 23, 23);
}
TEST(OsmlStreamParser, beginEndNested)
@@ -768,29 +852,32 @@ TEST(OsmlStreamParser, beginEndNested)
// 0 1 2 3 4 5
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
-
- assertCommand(reader, "a", 7, 8);
- assertFieldStart(reader, false, 9, 10);
- assertData(reader, "b", 10, 11);
- assertFieldEnd(reader, 11, 12);
- assertFieldStart(reader, true, 13, 14);
- assertData(reader, "c", 13, 14);
- assertCommand(reader, "d", 22, 23);
- assertFieldStart(reader, false, 24, 25);
- assertData(reader, "e", 25, 26);
- assertFieldEnd(reader, 26, 27);
- assertFieldStart(reader, false, 27, 28);
- assertData(reader, "f", 28, 29);
- assertFieldEnd(reader, 29, 30);
- assertFieldStart(reader, true, 31, 32);
- assertCommand(reader, "g", 31, 33);
- assertFieldStart(reader, false, 33, 34);
- assertData(reader, "h", 34, 35);
- assertFieldEnd(reader, 35, 36);
- assertFieldEnd(reader, 42, 43);
- assertFieldEnd(reader, 49, 50);
- assertEnd(reader, 51, 51);
+ OsmlStreamParser parser(charReader, logger);
+
+ assertCommandStart(parser, "a", true, Variant::mapType{}, 7, 8);
+ assertFieldStart(parser, false, 9, 10);
+ assertData(parser, "b", 10, 11);
+ assertFieldEnd(parser, 11, 12);
+
+ assertData(parser, "c", 13, 14);
+
+ assertCommandStart(parser, "d", true, Variant::mapType{}, 22, 23);
+ assertFieldStart(parser, false, 24, 25);
+ assertData(parser, "e", 25, 26);
+ assertFieldEnd(parser, 26, 27);
+ assertFieldStart(parser, false, 27, 28);
+ assertData(parser, "f", 28, 29);
+ assertFieldEnd(parser, 29, 30);
+
+ assertEmptyData(parser);
+ assertCommand(parser, "g", 31, 33);
+ assertFieldStart(parser, false, 33, 34);
+ assertData(parser, "h", 34, 35);
+ assertFieldEnd(parser, 35, 36);
+ assertEmptyData(parser);
+ assertRangeEnd(parser, 42, 43);
+ assertRangeEnd(parser, 49, 50);
+ assertEnd(parser, 51, 51);
}
TEST(OsmlStreamParser, beginEndWithCommand)
@@ -800,16 +887,75 @@ TEST(OsmlStreamParser, beginEndWithCommand)
// 0 1 2
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertCommand(reader, "book", 7, 11);
- assertFieldStart(reader, true, 12, 13);
- assertCommand(reader, "a", 12, 14);
- assertFieldStart(reader, false, 14, 15);
- assertData(reader, "test", 15, 19);
- assertFieldEnd(reader, 19, 20);
- assertFieldEnd(reader, 25, 29);
- assertEnd(reader, 30, 30);
+ assertCommandStart(parser, "book", true, Variant::mapType{}, 7, 11);
+ assertCommand(parser, "a", 12, 14);
+ assertFieldStart(parser, false, 14, 15);
+ assertData(parser, "test", 15, 19);
+ assertFieldEnd(parser, 19, 20);
+ assertRangeEnd(parser, 25, 29);
+ assertEnd(parser, 30, 30);
+}
+
+TEST(OsmlStreamParser, beginEndNestedFields)
+{
+ const char *testString = "\\begin{book}a{{b{c}}}\\end{book}";
+ // 012345678901234567890 1234567890
+ // 0 1 2 3
+ CharReader charReader(testString);
+ OsmlStreamParser parser(charReader, logger);
+ logger.reset();
+
+ assertCommandStart(parser, "book", true, Variant::mapType{}, 7, 11);
+ assertData(parser, "a", 12, 13);
+ assertFieldStart(parser, false, 13, 14);
+ assertFieldStart(parser, false, 14, 15);
+ assertData(parser, "b", 15, 16);
+ assertFieldStart(parser, false, 16, 17);
+ assertData(parser, "c", 17, 18);
+ assertFieldEnd(parser, 18, 19);
+ assertFieldEnd(parser, 19, 20);
+ assertFieldEnd(parser, 20, 21);
+ assertRangeEnd(parser, 26, 30);
+ assertEnd(parser, 31, 31);
+}
+
+TEST(OsmlStreamParser, errorBeginEndUnbalancedNestedFields)
+{
+ const char *testString = "\\begin{book}a{{b{c}}\\end{book}";
+ // 012345678901234567890 123456789
+ // 0 1 2
+ CharReader charReader(testString);
+ OsmlStreamParser parser(charReader, logger);
+ logger.reset();
+
+ assertCommandStart(parser, "book", true, Variant::mapType{}, 7, 11);
+ assertData(parser, "a", 12, 13);
+ assertFieldStart(parser, false, 13, 14);
+ assertFieldStart(parser, false, 14, 15);
+ assertData(parser, "b", 15, 16);
+ assertFieldStart(parser, false, 16, 17);
+ assertData(parser, "c", 17, 18);
+ assertFieldEnd(parser, 18, 19);
+ assertFieldEnd(parser, 19, 20);
+ ASSERT_THROW(assertRangeEnd(parser, 25, 29), LoggableException);
+}
+
+TEST(OsmlStreamParser, errorBeginEndUnbalancedFields)
+{
+ const char *testString = "{a";
+ // 01
+ CharReader charReader(testString);
+ OsmlStreamParser parser(charReader, logger);
+
+ logger.reset();
+
+ assertFieldStart(parser, false, 0, 1);
+ assertTextData(parser, "a", 1, 2, 1, 2, WhitespaceMode::PRESERVE);
+ ASSERT_FALSE(logger.hasError());
+ assertEnd(parser, 2, 2);
+ ASSERT_TRUE(logger.hasError());
}
TEST(OsmlStreamParser, errorBeginNoBraceOpen)
@@ -818,12 +964,13 @@ TEST(OsmlStreamParser, errorBeginNoBraceOpen)
// 01234567
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
ASSERT_FALSE(logger.hasError());
- assertData(reader, "a", 7, 8);
+ assertData(parser, "a", 7, 8);
ASSERT_TRUE(logger.hasError());
+ assertEnd(parser, 8, 8);
}
TEST(OsmlStreamParser, errorBeginNoIdentifier)
@@ -831,11 +978,11 @@ TEST(OsmlStreamParser, errorBeginNoIdentifier)
const char *testString = "\\begin{!";
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
ASSERT_FALSE(logger.hasError());
- ASSERT_THROW(reader.parse(), LoggableException);
+ ASSERT_THROW(parser.parse(), LoggableException);
ASSERT_TRUE(logger.hasError());
}
@@ -844,11 +991,11 @@ TEST(OsmlStreamParser, errorBeginNoBraceClose)
const char *testString = "\\begin{a";
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
ASSERT_FALSE(logger.hasError());
- ASSERT_THROW(reader.parse(), LoggableException);
+ ASSERT_THROW(parser.parse(), LoggableException);
ASSERT_TRUE(logger.hasError());
}
@@ -857,15 +1004,15 @@ TEST(OsmlStreamParser, errorBeginNoName)
const char *testString = "\\begin{a#}";
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
ASSERT_FALSE(logger.hasError());
- assertCommand(reader, "a");
+ assertCommandStart(parser, "a", true);
ASSERT_TRUE(logger.hasError());
logger.reset();
ASSERT_FALSE(logger.hasError());
- assertEnd(reader);
+ assertEnd(parser);
ASSERT_TRUE(logger.hasError());
}
@@ -875,11 +1022,11 @@ TEST(OsmlStreamParser, errorEndNoBraceOpen)
// 012345
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
ASSERT_FALSE(logger.hasError());
- assertData(reader, "a", 5, 6);
+ assertData(parser, "a", 5, 6);
ASSERT_TRUE(logger.hasError());
}
@@ -888,11 +1035,11 @@ TEST(OsmlStreamParser, errorEndNoIdentifier)
const char *testString = "\\end{!";
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
ASSERT_FALSE(logger.hasError());
- ASSERT_THROW(reader.parse(), LoggableException);
+ ASSERT_THROW(parser.parse(), LoggableException);
ASSERT_TRUE(logger.hasError());
}
@@ -901,11 +1048,11 @@ TEST(OsmlStreamParser, errorEndNoBraceClose)
const char *testString = "\\end{a";
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
ASSERT_FALSE(logger.hasError());
- ASSERT_THROW(reader.parse(), LoggableException);
+ ASSERT_THROW(parser.parse(), LoggableException);
ASSERT_TRUE(logger.hasError());
}
@@ -914,11 +1061,11 @@ TEST(OsmlStreamParser, errorEndNoBegin)
const char *testString = "\\end{a}";
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
ASSERT_FALSE(logger.hasError());
- ASSERT_THROW(reader.parse(), LoggableException);
+ ASSERT_THROW(parser.parse(), LoggableException);
ASSERT_TRUE(logger.hasError());
}
@@ -929,16 +1076,15 @@ TEST(OsmlStreamParser, errorBeginEndMismatch)
// 0 1 2 3
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
- assertCommand(reader, "a", 7, 8);
- assertFieldStart(reader, true, 10, 11);
- assertCommand(reader, "b", 17, 18);
- assertFieldStart(reader, true, 20, 24);
- assertData(reader, "test", 20, 24);
+ assertCommandStart(parser, "a", true, Variant::mapType{}, 7, 8);
+ assertEmptyData(parser);
+ assertCommandStart(parser, "b", true, Variant::mapType{}, 17, 18);
+ assertData(parser, "test", 20, 24);
ASSERT_FALSE(logger.hasError());
- ASSERT_THROW(reader.parse(), LoggableException);
+ ASSERT_THROW(parser.parse(), LoggableException);
ASSERT_TRUE(logger.hasError());
}
@@ -948,10 +1094,10 @@ TEST(OsmlStreamParser, commandWithNSSep)
// 012345678901
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertCommand(reader, "test1:test2", 0, 12);
- assertEnd(reader, 12, 12);
+ assertCommand(parser, "test1:test2", 0, 12);
+ assertEnd(parser, 12, 12);
}
TEST(OsmlStreamParser, beginEndWithNSSep)
@@ -961,12 +1107,11 @@ TEST(OsmlStreamParser, beginEndWithNSSep)
// 0 1 2 3
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertCommand(reader, "test1:test2", 7, 18);
- assertFieldStart(reader, true, 19, 20);
- assertFieldEnd(reader, 24, 35);
- assertEnd(reader, 36, 36);
+ assertCommandStart(parser, "test1:test2", true, Variant::mapType{}, 7, 18);
+ assertRangeEnd(parser, 24, 35);
+ assertEnd(parser, 36, 36);
}
TEST(OsmlStreamParser, errorBeginNSSep)
@@ -974,15 +1119,14 @@ TEST(OsmlStreamParser, errorBeginNSSep)
const char *testString = "\\begin:test{blub}\\end{blub}";
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
ASSERT_FALSE(logger.hasError());
- assertCommand(reader, "blub");
+ assertCommandStart(parser, "blub", true, Variant::mapType{});
ASSERT_TRUE(logger.hasError());
- assertFieldStart(reader, true);
- assertFieldEnd(reader);
- assertEnd(reader);
+ assertRangeEnd(parser);
+ assertEnd(parser);
}
TEST(OsmlStreamParser, errorEndNSSep)
@@ -990,15 +1134,14 @@ TEST(OsmlStreamParser, errorEndNSSep)
const char *testString = "\\begin{blub}\\end:test{blub}";
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
- assertCommand(reader, "blub");
- assertFieldStart(reader, true);
+ assertCommandStart(parser, "blub", true, Variant::mapType{});
ASSERT_FALSE(logger.hasError());
- assertFieldEnd(reader);
+ assertRangeEnd(parser);
ASSERT_TRUE(logger.hasError());
- assertEnd(reader);
+ assertEnd(parser);
}
TEST(OsmlStreamParser, errorEmptyNs)
@@ -1006,14 +1149,14 @@ TEST(OsmlStreamParser, errorEmptyNs)
const char *testString = "\\test:";
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
ASSERT_FALSE(logger.hasError());
- assertCommand(reader, "test");
+ assertCommand(parser, "test");
ASSERT_TRUE(logger.hasError());
- assertData(reader, ":");
- assertEnd(reader);
+ assertData(parser, ":");
+ assertEnd(parser);
}
TEST(OsmlStreamParser, errorRepeatedNs)
@@ -1021,14 +1164,14 @@ TEST(OsmlStreamParser, errorRepeatedNs)
const char *testString = "\\test::";
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
ASSERT_FALSE(logger.hasError());
- assertCommand(reader, "test");
+ assertCommand(parser, "test");
ASSERT_TRUE(logger.hasError());
- assertData(reader, "::");
- assertEnd(reader);
+ assertData(parser, "::");
+ assertEnd(parser);
}
TEST(OsmlStreamParser, explicitDefaultField)
@@ -1037,14 +1180,14 @@ TEST(OsmlStreamParser, explicitDefaultField)
// 01234567
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertCommand(reader, "a", 0, 2);
- assertFieldStart(reader, true, 2, 4);
- assertData(reader, "b", 4, 5);
- assertFieldEnd(reader, 5, 6);
- assertData(reader, "c", 6, 7);
- assertEnd(reader, 7, 7);
+ assertCommand(parser, "a", 0, 2);
+ assertFieldStart(parser, true, 2, 4);
+ assertData(parser, "b", 4, 5);
+ assertFieldEnd(parser, 5, 6);
+ assertData(parser, "c", 6, 7);
+ assertEnd(parser, 7, 7);
}
TEST(OsmlStreamParser, explicitDefaultFieldWithCommand)
@@ -1053,33 +1196,33 @@ TEST(OsmlStreamParser, explicitDefaultFieldWithCommand)
// 0123 4567
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertCommand(reader, "a", 0, 2);
- assertFieldStart(reader, true, 2, 4);
- assertCommand(reader, "b", 4, 6);
- assertFieldEnd(reader, 6, 7);
- assertData(reader, "c", 7, 8);
- assertEnd(reader, 8, 8);
+ assertCommand(parser, "a", 0, 2);
+ assertFieldStart(parser, true, 2, 4);
+ assertCommand(parser, "b", 4, 6);
+ assertFieldEnd(parser, 6, 7);
+ assertData(parser, "c", 7, 8);
+ assertEnd(parser, 8, 8);
}
-TEST(OsmlStreamParser, errorFieldAfterExplicitDefaultField)
+TEST(OsmlStreamParser, fieldAfterExplicitDefaultField)
{
const char *testString = "\\a{!\\b}{c}";
// 0123 456789
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
- assertCommand(reader, "a", 0, 2);
- assertFieldStart(reader, true, 2, 4);
- assertCommand(reader, "b", 4, 6);
- assertFieldEnd(reader, 6, 7);
- ASSERT_FALSE(logger.hasError());
- assertData(reader, "c", 8, 9);
- ASSERT_TRUE(logger.hasError());
- assertEnd(reader, 10, 10);
+ assertCommand(parser, "a", 0, 2);
+ assertFieldStart(parser, true, 2, 4);
+ assertCommand(parser, "b", 4, 6);
+ assertFieldEnd(parser, 6, 7);
+ assertFieldStart(parser, false, 7, 8);
+ assertData(parser, "c", 8, 9);
+ assertFieldEnd(parser, 9, 10);
+ assertEnd(parser, 10, 10);
}
TEST(OsmlStreamParser, annotationStart)
@@ -1089,10 +1232,10 @@ TEST(OsmlStreamParser, annotationStart)
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertAnnotationStart(reader, "a", Variant::mapType{}, 0, 3);
- assertEnd(reader, 3, 3);
+ assertAnnotationStart(parser, "a", Variant::mapType{}, 0, 3);
+ assertEnd(parser, 3, 3);
}
TEST(OsmlStreamParser, annotationStartWithName)
@@ -1103,11 +1246,11 @@ TEST(OsmlStreamParser, annotationStartWithName)
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertAnnotationStart(reader, "annotationWithName",
+ assertAnnotationStart(parser, "annotationWithName",
Variant::mapType{{"name", "aName"}}, 0, 20);
- assertEnd(reader, 26, 26);
+ assertEnd(parser, 26, 26);
}
TEST(OsmlStreamParser, annotationStartWithArguments)
@@ -1118,12 +1261,12 @@ TEST(OsmlStreamParser, annotationStartWithArguments)
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
assertAnnotationStart(
- reader, "annotationWithName",
+ parser, "annotationWithName",
Variant::mapType{{"name", "aName"}, {"a", 1}, {"b", 2}}, 0, 20);
- assertEnd(reader, 35, 35);
+ assertEnd(parser, 35, 35);
}
TEST(OsmlStreamParser, simpleAnnotationStartBeginEnd)
@@ -1134,16 +1277,16 @@ TEST(OsmlStreamParser, simpleAnnotationStartBeginEnd)
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
assertAnnotationStart(
- reader, "ab", Variant::mapType{{"name", "name"}, {"a", 1}, {"b", 2}}, 8,
+ parser, "ab", Variant::mapType{{"name", "name"}, {"a", 1}, {"b", 2}}, 8,
10);
- assertFieldStart(reader, true, 26, 27);
- assertData(reader, "a", 26, 27);
- assertFieldEnd(reader, 33, 35);
- assertAnnotationEnd(reader, "", "", 36, 38);
- assertEnd(reader, 38, 38);
+ ASSERT_TRUE(parser.inRangeCommand());
+ assertData(parser, "a", 26, 27);
+ assertRangeEnd(parser, 33, 35);
+ assertAnnotationEnd(parser, "", "", 36, 38);
+ assertEnd(parser, 38, 38);
}
TEST(OsmlStreamParser, annotationEnd)
@@ -1153,10 +1296,10 @@ TEST(OsmlStreamParser, annotationEnd)
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertAnnotationEnd(reader, "a", "", 0, 2);
- assertEnd(reader, 3, 3);
+ assertAnnotationEnd(parser, "a", "", 0, 2);
+ assertEnd(parser, 3, 3);
}
TEST(OsmlStreamParser, annotationEndWithName)
@@ -1166,10 +1309,10 @@ TEST(OsmlStreamParser, annotationEndWithName)
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertAnnotationEnd(reader, "a", "name", 0, 2);
- assertEnd(reader, 8, 8);
+ assertAnnotationEnd(parser, "a", "name", 0, 2);
+ assertEnd(parser, 8, 8);
}
TEST(OsmlStreamParser, annotationEndWithNameAsArgs)
@@ -1179,10 +1322,10 @@ TEST(OsmlStreamParser, annotationEndWithNameAsArgs)
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertAnnotationEnd(reader, "a", "name", 0, 2);
- assertEnd(reader, 14, 14);
+ assertAnnotationEnd(parser, "a", "name", 0, 2);
+ assertEnd(parser, 14, 14);
}
TEST(OsmlStreamParser, errorAnnotationEndWithArguments)
@@ -1193,14 +1336,15 @@ TEST(OsmlStreamParser, errorAnnotationEndWithArguments)
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
logger.reset();
ASSERT_FALSE(logger.hasError());
- assertCommand(reader, "a", Variant::mapType{{"foo", "bar"}}, 0, 2);
+ assertCommandStart(parser, "a", false, Variant::mapType{{"foo", "bar"}}, 0,
+ 2);
ASSERT_TRUE(logger.hasError());
- assertData(reader, ">", 11, 12);
- assertEnd(reader, 12, 12);
+ assertData(parser, ">", 11, 12);
+ assertEnd(parser, 12, 12);
}
TEST(OsmlStreamParser, closingAnnotation)
@@ -1210,11 +1354,11 @@ TEST(OsmlStreamParser, closingAnnotation)
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
- assertAnnotationStart(reader, "a", Variant::mapType{}, 0, 3);
- assertData(reader, ">", 3, 4);
- assertEnd(reader, 4, 4);
+ assertAnnotationStart(parser, "a", Variant::mapType{}, 0, 3);
+ assertData(parser, ">", 3, 4);
+ assertEnd(parser, 4, 4);
}
TEST(OsmlStreamParser, annotationWithFields)
@@ -1225,23 +1369,23 @@ TEST(OsmlStreamParser, annotationWithFields)
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
-
- assertData(reader, "a", 0, 1);
- assertAnnotationStart(reader, "b", Variant::mapType{}, 2, 5);
- assertFieldStart(reader, false, 5, 6);
- assertData(reader, "c", 6, 7);
- assertFieldEnd(reader, 7, 8);
- assertFieldStart(reader, false, 8, 9);
- assertData(reader, "d", 9, 10);
- assertFieldEnd(reader, 10, 11);
- assertFieldStart(reader, true, 11, 13);
- assertData(reader, "e", 13, 14);
- assertFieldEnd(reader, 14, 15);
- assertData(reader, "f", 16, 17);
- assertAnnotationEnd(reader, "", "", 18, 20);
- assertData(reader, "g", 21, 22);
- assertEnd(reader, 22, 22);
+ OsmlStreamParser parser(charReader, logger);
+
+ assertData(parser, "a", 0, 1);
+ assertAnnotationStart(parser, "b", Variant::mapType{}, 2, 5);
+ assertFieldStart(parser, false, 5, 6);
+ assertData(parser, "c", 6, 7);
+ assertFieldEnd(parser, 7, 8);
+ assertFieldStart(parser, false, 8, 9);
+ assertData(parser, "d", 9, 10);
+ assertFieldEnd(parser, 10, 11);
+ assertFieldStart(parser, true, 11, 13);
+ assertData(parser, "e", 13, 14);
+ assertFieldEnd(parser, 14, 15);
+ assertData(parser, "f", 16, 17);
+ assertAnnotationEnd(parser, "", "", 18, 20);
+ assertData(parser, "g", 21, 22);
+ assertEnd(parser, 22, 22);
}
TEST(OsmlStreamParser, annotationStartEscape)
@@ -1252,10 +1396,44 @@ TEST(OsmlStreamParser, annotationStartEscape)
CharReader charReader(testString);
- OsmlStreamParser reader(charReader, logger);
+ OsmlStreamParser parser(charReader, logger);
+
+ assertData(parser, "<%test", 0, 7);
+ assertEnd(parser, 7, 7);
+}
- assertData(reader, "<%test", 0, 7);
- assertEnd(reader, 7, 7);
+TEST(OsmlStreamParser, userDefinedTokens)
+{
+ const char *testString = "<<My dear fellows>>, the *old man* said.";
+ // 0123456789012345678901234567890123456789
+ // 0 1 2 3
+
+ CharReader charReader(testString);
+
+ OsmlStreamParser parser(charReader, logger);
+
+ TokenId tSpeechStart = parser.registerToken("<<");
+ TokenId tSpeechEnd = parser.registerToken(">>");
+ TokenId tStar = parser.registerToken("*");
+
+ ASSERT_TRUE(tSpeechStart != Tokens::Empty);
+ ASSERT_TRUE(tSpeechEnd != Tokens::Empty);
+ ASSERT_TRUE(tStar != Tokens::Empty);
+
+ TokenSet tokens{tSpeechStart, tSpeechEnd, tStar};
+
+ ASSERT_EQ(OsmlStreamParser::State::DATA, parser.parse());
+ TokenizedDataReader reader = parser.getData().reader();
+
+ assertToken(reader, tSpeechStart, "<<", tokens, WhitespaceMode::PRESERVE, 0, 2);
+ assertText(reader, "My dear fellows", tokens, WhitespaceMode::PRESERVE, 2, 17);
+ assertToken(reader, tSpeechEnd, ">>", tokens, WhitespaceMode::PRESERVE, 17, 19);
+ assertText(reader, ", the ", tokens, WhitespaceMode::PRESERVE, 19, 25);
+ assertToken(reader, tStar, "*", tokens, WhitespaceMode::PRESERVE, 25, 26);
+ assertText(reader, "old man", tokens, WhitespaceMode::PRESERVE, 26, 33);
+ assertToken(reader, tStar, "*", tokens, WhitespaceMode::PRESERVE, 33, 34);
+ assertText(reader, " said.", tokens, WhitespaceMode::PRESERVE, 34, 40);
+ assertEnd(reader);
}
}
diff --git a/test/formats/osxml/OsxmlEventParserTest.cpp b/test/formats/osxml/OsxmlEventParserTest.cpp
index 3293370..d4e9443 100644
--- a/test/formats/osxml/OsxmlEventParserTest.cpp
+++ b/test/formats/osxml/OsxmlEventParserTest.cpp
@@ -21,6 +21,7 @@
#include <core/frontend/TerminalLogger.hpp>
#include <core/common/CharReader.hpp>
#include <core/common/Variant.hpp>
+#include <core/parser/utils/TokenizedData.hpp>
#include <formats/osxml/OsxmlEventParser.hpp>
@@ -31,10 +32,10 @@ static TerminalLogger logger(std::cerr, true);
namespace {
enum class OsxmlEvent {
- COMMAND,
+ COMMAND_START,
ANNOTATION_START,
ANNOTATION_END,
- FIELD_END,
+ RANGE_END,
DATA
};
@@ -42,9 +43,10 @@ class TestOsxmlEventListener : public OsxmlEvents {
public:
std::vector<std::pair<OsxmlEvent, Variant>> events;
- void command(const Variant &name, const Variant::mapType &args) override
+ void commandStart(const Variant &name,
+ const Variant::mapType &args) override
{
- events.emplace_back(OsxmlEvent::COMMAND,
+ events.emplace_back(OsxmlEvent::COMMAND_START,
Variant::arrayType{name, args});
}
@@ -62,25 +64,30 @@ public:
Variant::arrayType{className, elementName});
}
- void fieldEnd() override
+ void rangeEnd() override
{
- events.emplace_back(OsxmlEvent::FIELD_END, Variant::arrayType{});
+ events.emplace_back(OsxmlEvent::RANGE_END, Variant::arrayType{});
}
- void data(const Variant &data) override
+ void data(const TokenizedData &data) override
{
- events.emplace_back(OsxmlEvent::DATA, Variant::arrayType{data});
+ Token token;
+ Variant text;
+ TokenizedDataReader reader = data.reader();
+ reader.read(token, TokenSet{}, WhitespaceMode::PRESERVE);
+ EXPECT_EQ(Tokens::Data, token.id);
+ text = Variant::fromString(token.content);
+ text.setLocation(token.getLocation());
+ events.emplace_back(OsxmlEvent::DATA, Variant::arrayType{text});
}
};
static std::vector<std::pair<OsxmlEvent, Variant>> parseXml(
- const char *testString,
- WhitespaceMode whitespaceMode = WhitespaceMode::TRIM)
+ const char *testString)
{
TestOsxmlEventListener listener;
CharReader reader(testString);
OsxmlEventParser parser(reader, listener, logger);
- parser.setWhitespaceMode(whitespaceMode);
parser.parse();
return listener.events;
}
@@ -93,11 +100,11 @@ TEST(OsxmlEventParser, simpleCommandWithArgs)
// 0 1 2 3
std::vector<std::pair<OsxmlEvent, Variant>> expectedEvents{
- {OsxmlEvent::COMMAND,
+ {OsxmlEvent::COMMAND_START,
Variant::arrayType{
"a", Variant::mapType{
{"name", "test"}, {"a", 1}, {"b", 2}, {"c", "blub"}}}},
- {OsxmlEvent::FIELD_END, Variant::arrayType{}}};
+ {OsxmlEvent::RANGE_END, Variant::arrayType{}}};
auto events = parseXml(testString);
ASSERT_EQ(expectedEvents, events);
@@ -133,10 +140,12 @@ TEST(OsxmlEventParser, magicTopLevelTag)
const char *testString = "<ousia><a/><b/></ousia>";
std::vector<std::pair<OsxmlEvent, Variant>> expectedEvents{
- {OsxmlEvent::COMMAND, Variant::arrayType{{"a", Variant::mapType{}}}},
- {OsxmlEvent::FIELD_END, Variant::arrayType{}},
- {OsxmlEvent::COMMAND, Variant::arrayType{{"b", Variant::mapType{}}}},
- {OsxmlEvent::FIELD_END, Variant::arrayType{}}};
+ {OsxmlEvent::COMMAND_START,
+ Variant::arrayType{{"a", Variant::mapType{}}}},
+ {OsxmlEvent::RANGE_END, Variant::arrayType{}},
+ {OsxmlEvent::COMMAND_START,
+ Variant::arrayType{{"b", Variant::mapType{}}}},
+ {OsxmlEvent::RANGE_END, Variant::arrayType{}}};
auto events = parseXml(testString);
ASSERT_EQ(expectedEvents, events);
@@ -147,71 +156,35 @@ TEST(OsxmlEventParser, magicTopLevelTagInside)
const char *testString = "<a><ousia/></a>";
std::vector<std::pair<OsxmlEvent, Variant>> expectedEvents{
- {OsxmlEvent::COMMAND, Variant::arrayType{{"a", Variant::mapType{}}}},
- {OsxmlEvent::COMMAND,
+ {OsxmlEvent::COMMAND_START,
+ Variant::arrayType{{"a", Variant::mapType{}}}},
+ {OsxmlEvent::COMMAND_START,
Variant::arrayType{{"ousia", Variant::mapType{}}}},
- {OsxmlEvent::FIELD_END, Variant::arrayType{}},
- {OsxmlEvent::FIELD_END, Variant::arrayType{}}};
+ {OsxmlEvent::RANGE_END, Variant::arrayType{}},
+ {OsxmlEvent::RANGE_END, Variant::arrayType{}}};
auto events = parseXml(testString);
ASSERT_EQ(expectedEvents, events);
}
-TEST(OsxmlEventParser, commandWithDataPreserveWhitespace)
+TEST(OsxmlEventParser, commandWithData)
{
const char *testString = "<a> hello \n world </a>";
// 012345678901 234567890123
// 0 1 2
std::vector<std::pair<OsxmlEvent, Variant>> expectedEvents{
- {OsxmlEvent::COMMAND, Variant::arrayType{"a", Variant::mapType{}}},
+ {OsxmlEvent::COMMAND_START,
+ Variant::arrayType{"a", Variant::mapType{}}},
{OsxmlEvent::DATA, Variant::arrayType{" hello \n world "}},
- {OsxmlEvent::FIELD_END, Variant::arrayType{}}};
+ {OsxmlEvent::RANGE_END, Variant::arrayType{}}};
- auto events = parseXml(testString, WhitespaceMode::PRESERVE);
+ auto events = parseXml(testString);
ASSERT_EQ(expectedEvents, events);
// Check the location of the text
ASSERT_EQ(3U, events[1].second.asArray()[0].getLocation().getStart());
ASSERT_EQ(20U, events[1].second.asArray()[0].getLocation().getEnd());
}
-
-TEST(OsxmlEventParser, commandWithDataTrimWhitespace)
-{
- const char *testString = "<a> hello \n world </a>";
- // 012345678901 234567890123
- // 0 1 2
-
- std::vector<std::pair<OsxmlEvent, Variant>> expectedEvents{
- {OsxmlEvent::COMMAND, Variant::arrayType{"a", Variant::mapType{}}},
- {OsxmlEvent::DATA, Variant::arrayType{"hello \n world"}},
- {OsxmlEvent::FIELD_END, Variant::arrayType{}}};
-
- auto events = parseXml(testString, WhitespaceMode::TRIM);
- ASSERT_EQ(expectedEvents, events);
-
- // Check the location of the text
- ASSERT_EQ(5U, events[1].second.asArray()[0].getLocation().getStart());
- ASSERT_EQ(19U, events[1].second.asArray()[0].getLocation().getEnd());
-}
-
-TEST(OsxmlEventParser, commandWithDataCollapseWhitespace)
-{
- const char *testString = "<a> hello \n world </a>";
- // 012345678901 234567890123
- // 0 1 2
-
- std::vector<std::pair<OsxmlEvent, Variant>> expectedEvents{
- {OsxmlEvent::COMMAND, Variant::arrayType{"a", Variant::mapType{}}},
- {OsxmlEvent::DATA, Variant::arrayType{"hello world"}},
- {OsxmlEvent::FIELD_END, Variant::arrayType{}}};
-
- auto events = parseXml(testString, WhitespaceMode::COLLAPSE);
- ASSERT_EQ(expectedEvents, events);
-
- // Check the location of the text
- ASSERT_EQ(5U, events[1].second.asArray()[0].getLocation().getStart());
- ASSERT_EQ(19U, events[1].second.asArray()[0].getLocation().getEnd());
-}
}
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-30 21:13:04 +0000