Skip to content

feat(syllabifier): trim leading delimiters #1147

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ksqsf wants to merge 1 commit into
base: master
Choose a base branch
from
Open

feat(syllabifier): trim leading delimiters #1147

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 11 additions & 3 deletions src/rime/algo/syllabifier.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,12 +53,19 @@ int Syllabifier::BuildSyllableGraph(const string& input,

if (current_pos > farthest)
farthest = current_pos;
DLOG(INFO) << "current_pos: " << current_pos;

// consume leading delimiters
size_t begin_pos = current_pos;
while (begin_pos < input.length() &&
delimiters_.find(input[begin_pos]) != string::npos)
++begin_pos;
DLOG(INFO) << "current_pos: " << current_pos
<< ", begin_pos: " << begin_pos;

// see where we can go by advancing a syllable
vector<Prism::Match> matches;
set<SyllableId> exact_match_syllables;
auto current_input = input.substr(current_pos);
auto current_input = input.substr(begin_pos);
prism.CommonPrefixSearch(current_input, &matches);
if (corrector_) {
for (auto& m : matches) {
Expand All @@ -78,12 +85,13 @@ int Syllabifier::BuildSyllableGraph(const string& input,
}
}

size_t leading_gap = begin_pos - current_pos;
if (!matches.empty()) {
auto& end_vertices(graph->edges[current_pos]);
for (const auto& m : matches) {
if (m.length == 0)
continue;
size_t end_pos = current_pos + m.length;
size_t end_pos = current_pos + leading_gap + m.length;
// consume trailing delimiters
while (end_pos < input.length() &&
delimiters_.find(input[end_pos]) != string::npos)
Expand Down
2 changes: 1 addition & 1 deletion src/rime/gear/abc_segmentor.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ bool AbcSegmentor::Proceed(Segmentation* segmentation) {
bool expecting_an_initial = true;
for (; k < input.length(); ++k) {
bool is_letter = alphabet_.find(input[k]) != string::npos;
bool is_delimiter = (k != j) && (delimiter_.find(input[k]) != string::npos);
bool is_delimiter = (k != 0) && (delimiter_.find(input[k]) != string::npos);
if (!is_letter && !is_delimiter)
break;
bool is_initial = initials_.find(input[k]) != string::npos;
Expand Down
51 changes: 51 additions & 0 deletions test/syllabifier_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -160,3 +160,54 @@ TEST_F(RimeSyllabifierTest, TransposedSyllableGraph) {
ASSERT_FALSE(NULL == g.indices[0][syllable_id_["chan"]][0]);
EXPECT_EQ(4, g.indices[0][syllable_id_["chan"]][0]->end_pos);
}

TEST_F(RimeSyllabifierTest, TrimLeadingDelimiters) {
rime::Syllabifier s(" '");
rime::SyllableGraph g;
const rime::string input("''a");
s.BuildSyllableGraph(input, *prism_, &g);
EXPECT_EQ(input.length(), g.input_length);
EXPECT_EQ(input.length(), g.interpreted_length);
EXPECT_EQ(2, g.vertices.size());
ASSERT_FALSE(g.vertices.end() == g.vertices.find(3));
EXPECT_EQ(rime::kNormalSpelling, g.vertices[1]);
rime::SpellingMap& sp(g.edges[0][3]);
EXPECT_EQ(1, sp.size());
ASSERT_FALSE(sp.end() == sp.find(syllable_id_["a"]));
EXPECT_EQ(rime::kNormalSpelling, sp[0].type);
EXPECT_EQ(0.0, sp[0].credibility);
}

TEST_F(RimeSyllabifierTest, TrimTrailingDelimiters) {
rime::Syllabifier s(" '");
rime::SyllableGraph g;
const rime::string input("a''");
s.BuildSyllableGraph(input, *prism_, &g);
EXPECT_EQ(input.length(), g.input_length);
EXPECT_EQ(input.length(), g.interpreted_length);
EXPECT_EQ(2, g.vertices.size());
ASSERT_FALSE(g.vertices.end() == g.vertices.find(3));
EXPECT_EQ(rime::kNormalSpelling, g.vertices[1]);
rime::SpellingMap& sp(g.edges[0][3]);
EXPECT_EQ(1, sp.size());
ASSERT_FALSE(sp.end() == sp.find(syllable_id_["a"]));
EXPECT_EQ(rime::kNormalSpelling, sp[0].type);
EXPECT_EQ(0.0, sp[0].credibility);
}

TEST_F(RimeSyllabifierTest, TrimBothLeadingAndTrailingDelimiters) {
rime::Syllabifier s(" '");
rime::SyllableGraph g;
const rime::string input("''a''");
s.BuildSyllableGraph(input, *prism_, &g);
EXPECT_EQ(input.length(), g.input_length);
EXPECT_EQ(input.length(), g.interpreted_length);
EXPECT_EQ(2, g.vertices.size());
ASSERT_FALSE(g.vertices.end() == g.vertices.find(5));
EXPECT_EQ(rime::kNormalSpelling, g.vertices[1]);
rime::SpellingMap& sp(g.edges[0][5]);
EXPECT_EQ(1, sp.size());
ASSERT_FALSE(sp.end() == sp.find(syllable_id_["a"]));
EXPECT_EQ(rime::kNormalSpelling, sp[0].type);
EXPECT_EQ(0.0, sp[0].credibility);
}
Loading