| /external/libtextclassifier/lang_id/ |
| D | lang-id.cc | 70 int GetRealTextSize(const LightSentence &sentence) { in GetRealTextSize() argument
72 for (int i = 0; i < sentence.num_words(); ++i) { in GetRealTextSize()
73 TC_DCHECK(!sentence.word(i).empty()); in GetRealTextSize()
74 TC_DCHECK_EQ('^', sentence.word(i).front()); in GetRealTextSize()
75 TC_DCHECK_EQ('$', sentence.word(i).back()); in GetRealTextSize()
76 total += sentence.word(i).size() - 2; in GetRealTextSize()
204 LightSentence sentence; in ScoreLanguages() local
205 TokenizeTextForLangId(text, &sentence); in ScoreLanguages()
207 if (GetRealTextSize(sentence) < min_text_size_in_bytes_) { in ScoreLanguages()
214 lang_id_brain_interface_.GetFeatures(&sentence, &features); in ScoreLanguages()
|
| D | language-identifier-features.cc | 47 const LightSentence &sentence) const { in ComputeNgramCounts()
61 for (int i = 0; i < sentence.num_words(); ++i) { in ComputeNgramCounts()
62 const std::string &word = sentence.word(i); in ComputeNgramCounts()
118 const LightSentence &sentence, in Evaluate() argument
121 int total_count = ComputeNgramCounts(sentence); in Evaluate()
|
| D | lang-id-brain-interface.h | 62 void GetFeatures(LightSentence *sentence, in GetFeatures() argument
66 feature_extractor_.Preprocess(&workspace, sentence); in GetFeatures()
67 return feature_extractor_.ExtractFeatures(workspace, *sentence, features); in GetFeatures()
|
| D | relevant-script-feature.cc | 41 const LightSentence &sentence, in Evaluate() argument
53 for (int i = 0; i < sentence.num_words(); ++i) { in Evaluate()
54 const std::string &word = sentence.word(i); in Evaluate()
|
| D | language-identifier-features.h | 48 void Evaluate(const WorkspaceSet &workspaces, const LightSentence &sentence,
57 int ComputeNgramCounts(const LightSentence &sentence) const;
|
| D | custom-tokenizer.cc | 55 void TokenizeTextForLangId(const std::string &text, LightSentence *sentence) { in TokenizeTextForLangId() argument
80 std::string *word = sentence->add_word(); in TokenizeTextForLangId()
|
| D | custom-tokenizer.h | 36 void TokenizeTextForLangId(const std::string &text, LightSentence *sentence);
|
| D | relevant-script-feature.h | 47 void Evaluate(const WorkspaceSet &workspaces, const LightSentence &sentence,
|
| /external/python/cpython2/Lib/test/cjkencodings/ |
| D | hz-utf8.txt | 1 This sentence is in ASCII.
2 The next sentence is in GB.己所不欲，勿施於人。Bye.
|
| D | hz.txt | 1 This sentence is in ASCII.
2 The next sentence is in GB.~{<:Ky2;S{#,NpJ)l6HK!#~}Bye.
|
| /external/icu/icu4c/source/test/testdata/break_rules/ |
| D | sentence.txt | 6 # file: sentence.txt
8 type = sentence; # one of grapheme | word | line | sentence
|
| /external/icu/icu4c/source/test/cintltst/ |
| D | cbiapts.c | 151 UBreakIterator *word, *sentence, *line, *character, *b, *bogus; in TestBreakIteratorCAPI() local
180 sentence = ubrk_open(UBRK_SENTENCE, "en_US", text, u_strlen(text), &status); in TestBreakIteratorCAPI()
309 ubrk_first(sentence); in TestBreakIteratorCAPI()
310 pos = ubrk_current(sentence); in TestBreakIteratorCAPI()
312 pos = ubrk_last(sentence); in TestBreakIteratorCAPI()
316 ubrk_first(sentence); in TestBreakIteratorCAPI()
317 to = ubrk_following( sentence, 0 ); in TestBreakIteratorCAPI()
319 to = ubrk_preceding( sentence, to ); in TestBreakIteratorCAPI()
321 if (ubrk_first(sentence)!=ubrk_current(sentence)) { in TestBreakIteratorCAPI()
363 ubrk_close(sentence); in TestBreakIteratorCAPI()
|
| /external/icu/icu4j/demos/src/com/ibm/icu/dev/demo/translit/ |
| D | Demo.java | 699 String sentence = coreSentence.substring(oldPos, pos).trim(); in genTestFile() local
703 addSentenceToTable(out, sentence, in genTestFile()
770 static void addSentenceToTable(PrintWriter out, String sentence, in addSentenceToTable() argument
773 if (sentence.length() == 0) return; // skip empty lines in addSentenceToTable()
775 String originalShow = sentence; in addSentenceToTable()
777 latin = tl.transliterate(saveAscii.transliterate(sentence)); in addSentenceToTable()
790 String NFKDSentence = Normalizer.normalize(sentence, Normalizer.NFKD); in addSentenceToTable()
803 if (minLen > sentence.length()) minLen = sentence.length(); in addSentenceToTable()
806 if (reverse.charAt(i) != sentence.charAt(i)) break; in addSentenceToTable()
812 : showDifference(sentence, reverse); in addSentenceToTable()
[all …]
|
| /external/mesa3d/docs/specs/ |
| D | MESA_multithread_makecurrent.spec | 66 Replace the following sentence from section 2.2 Rendering Contexts:
78 Replace the following sentence from section 3.3.7 Rendering Contexts:
85 Replace the following sentence from section 3.5 Rendering Contexts:
|
| /external/icu/icu4c/source/data/brkitr/ |
| D | el.txt | 6 sentence:process(dependency){"sent_el.brk"}
|
| D | root.txt | 11 sentence:process(dependency){"sent.brk"}
|
| /external/snakeyaml/src/test/resources/pyyaml/ |
| D | spec-08-10.data | 7 This sentence
|
| D | spec-08-10.canonical | 11 : !!str "This sentence
|
| /external/llvm/test/YAMLParser/ |
| D | spec-08-10.test | 9 This sentence
|
| /external/svox/pico/tests/data/ |
| D | tests_regressions_es-ES.txt | 12 # TEST (old bug: burst of noise at end of sentence)
|
| /external/python/cpython2/Doc/library/ |
| D | textwrap.rst | 167 sentence endings and ensure that sentences are always separated by exactly
169 However, the sentence detection algorithm is imperfect: it assumes that a
170 sentence ending consists of a lowercase letter followed by one of ``'.'``,
183 Since the sentence detection algorithm relies on ``string.lowercase`` for
|
| /external/python/cpython2/Misc/ |
| D | README.Emacs | 29 sentence-end-double-space: t
|
| /external/icu/icu4c/source/test/testdata/ |
| D | rbbitst.txt | 14 # <sent> any following data is for sentence break testing
411 <data>•Here is a random sentence, no ending period<100></data>
414 <data>• (This is it). •Testing the sentence iterator. •\
416 •This is a simple sample sentence. •(This is it.) •This is a simple sample sentence. •\
418 Hi! •This is a simple sample sentence. •It does not have to make any sense as you can see. •Nel mez…
455 # Breaks around '(' following a sentence TERM. (Rule 9)
493 # test for bug #4152117: Make sure sentence breaking is handling
500 # sentence breaks for hindi which used Devanagari script
501 # make sure there is sentence break after ?,danda(hindi phrase separator),
513 # Try a few more of the less common sentence endings.
[all …]
|
| /external/icu/android_icu4j/src/main/tests/android/icu/dev/test/rbbi/ |
| D | rbbitst.txt | 14 # <sent> any following data is for sentence break testing
411 <data>•Here is a random sentence, no ending period<100></data>
414 <data>• (This is it). •Testing the sentence iterator. •\
416 •This is a simple sample sentence. •(This is it.) •This is a simple sample sentence. •\
418 Hi! •This is a simple sample sentence. •It does not have to make any sense as you can see. •Nel mez…
455 # Breaks around '(' following a sentence TERM. (Rule 9)
493 # test for bug #4152117: Make sure sentence breaking is handling
500 # sentence breaks for hindi which used Devanagari script
501 # make sure there is sentence break after ?,danda(hindi phrase separator),
513 # Try a few more of the less common sentence endings.
[all …]
|
| /external/icu/icu4j/main/tests/core/src/com/ibm/icu/dev/test/rbbi/ |
| D | rbbitst.txt | 14 # <sent> any following data is for sentence break testing
411 <data>•Here is a random sentence, no ending period<100></data>
414 <data>• (This is it). •Testing the sentence iterator. •\
416 •This is a simple sample sentence. •(This is it.) •This is a simple sample sentence. •\
418 Hi! •This is a simple sample sentence. •It does not have to make any sense as you can see. •Nel mez…
455 # Breaks around '(' following a sentence TERM. (Rule 9)
493 # test for bug #4152117: Make sure sentence breaking is handling
500 # sentence breaks for hindi which used Devanagari script
501 # make sure there is sentence break after ?,danda(hindi phrase separator),
513 # Try a few more of the less common sentence endings.
[all …]
|