Function ScoreOneScriptSpan

cld2/internal/scoreonescriptspan.cc:1302–1333

Score one scriptspan into doc_tote and vec, updating scoringcontext Inputs: One scriptspan of perhaps 40-60KB, all same script lower-case letters and single ASCII spaces. First character is a space to allow simple begining-of-word detect. End of buffer has three spaces and NUL to allow easy scan-to-end-of-word. Scoring context of scoring tables flags running boosts Outputs: Updated doc_tote giving

// the next-level-down routines.
//
void ScoreOneScriptSpan(const LangSpan& scriptspan,
                        ScoringContext* scoringcontext,
                        DocTote* doc_tote,
                        ResultChunkVector* vec) {
  if (scoringcontext->flags_cld2_verbose) {
    fprintf(scoringcontext->debug_file, "<br>ScoreOneScriptSpan(%s,%d) ",
            ULScriptCode(scriptspan.ulscript), scriptspan.text_bytes);
    // Optionally print the chunk lowercase letters/marks text
    string temp(&scriptspan.text[0], scriptspan.text_bytes);
    fprintf(scoringcontext->debug_file, "'%s'",
            GetHtmlEscapedText(temp).c_str());
    fprintf(scoringcontext->debug_file, "<br>\n");
  }
  scoringcontext->prior_chunk_lang = UNKNOWN_LANGUAGE;
  scoringcontext->oldest_distinct_boost = 0;
  ULScriptRType rtype = ULScriptRecognitionType(scriptspan.ulscript);
  if (scoringcontext->flags_cld2_score_as_quads && (rtype != RTypeCJK)) {
    rtype = RTypeMany;
  }
  switch (rtype) {
  case RTypeNone:
  case RTypeOne:
    ScoreEntireScriptSpan(scriptspan, scoringcontext, doc_tote, vec);
    break;
  case RTypeCJK:
    ScoreCJKScriptSpan(scriptspan, scoringcontext, doc_tote, vec);
    break;
  case RTypeMany:
    ScoreQuadScriptSpan(scriptspan, scoringcontext, doc_tote, vec);
    break;
  }
}

}       // End namespace CLD2