MCPcopy Create free account
hub / github.com/aboSamoor/pycld2 / ScoreEntireScriptSpan

Function ScoreEntireScriptSpan

cld2/internal/scoreonescriptspan.cc:1132–1160  ·  view source on GitHub ↗

Score RTypeNone or RTypeOne scriptspan into doc_tote and vec, updating scoringcontext

Source from the content-addressed store, hash-verified

1130// Score RTypeNone or RTypeOne scriptspan into doc_tote and vec, updating
1131// scoringcontext
1132void ScoreEntireScriptSpan(const LangSpan& scriptspan,
1133 ScoringContext* scoringcontext,
1134 DocTote* doc_tote,
1135 ResultChunkVector* vec) {
1136 int bytes = scriptspan.text_bytes;
1137 // Artificially set score to 1024 per 1KB, or 1 per byte
1138 int score = bytes;
1139 int reliability = 100;
1140 // doc_tote uses full languages
1141 Language one_one_lang = DefaultLanguage(scriptspan.ulscript);
1142 doc_tote->Add(one_one_lang, bytes, score, reliability);
1143
1144 if (scoringcontext->flags_cld2_html) {
1145 ChunkSummary chunksummary = {
1146 1, 0,
1147 one_one_lang, UNKNOWN_LANGUAGE, score, 1,
1148 bytes, 0, scriptspan.ulscript, reliability, reliability
1149 };
1150 CLD2_Debug(scriptspan.text, 1, scriptspan.text_bytes,
1151 false, false, NULL,
1152 scoringcontext, NULL, &chunksummary);
1153 }
1154
1155 // First byte is always a space
1156 JustOneItemToVector(scoringcontext->scanner, scriptspan.text,
1157 one_one_lang, 1, bytes - 1, vec);
1158
1159 scoringcontext->prior_chunk_lang = UNKNOWN_LANGUAGE;
1160}
1161
1162// Score RTypeCJK scriptspan into doc_tote and vec, updating scoringcontext
1163void ScoreCJKScriptSpan(const LangSpan& scriptspan,

Callers 1

ScoreOneScriptSpanFunction · 0.85

Calls 4

DefaultLanguageFunction · 0.85
JustOneItemToVectorFunction · 0.85
AddMethod · 0.80
CLD2_DebugFunction · 0.70

Tested by

no test coverage detected