GitHub/gf-core
1
0
Fork 1
mirror of https://github.com/GrammaticalFramework/gf-core.git synced 2026-05-23 09:52:55 -06:00
Code Issues Packages Projects Releases Wiki Activity

bugfix in the parser for lexical lookup

Browse Source
This commit is contained in:
krasimir
2015-06-30 12:54:19 +00:00
parent 6fc3114e3e
commit 974e152ac3
1 changed files with 51 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
src/runtime/c/pgf/parser.c
View File

@@ -1105,9 +1105,7 @@ pgf_parsing_lookahead(PgfParsing *ps, PgfParseState* state,
if (seq->idx != NULL) { if (seq->idx != NULL) {
PgfLexiconIdxEntry* entry = gu_buf_extend(state->lexicon_idx); PgfLexiconIdxEntry* entry = gu_buf_extend(state->lexicon_idx);
entry->idx = seq->idx; entry->idx = seq->idx;
entry->offset = entry->offset = (size_t) (current - ps->sentence);
(gu_seq_length(seq->syms) == 0) ? state->start_offset
: (size_t) (current - ps->sentence);
} }
if (len+1 <= max) if (len+1 <= max)
@@ -1179,9 +1177,23 @@ pgf_new_parse_state(PgfParsing* ps, size_t start_offset,
if (ps->before == NULL && start_offset == 0) if (ps->before == NULL && start_offset == 0)
state->needs_bind = false; state->needs_bind = false;
if (gu_seq_length(ps->concr->sequences) > 0) {
// Add epsilon lexical rules to the bottom up index
PgfSequence* seq = gu_seq_index(ps->concr->sequences, PgfSequence, 0);
if (gu_seq_length(seq->syms) == 0 && seq->idx != NULL) {
PgfLexiconIdxEntry* entry = gu_buf_extend(state->lexicon_idx);
entry->idx = seq->idx;
entry->offset = state->start_offset;
}
// Add non-epsilon lexical rules to the bottom up index
if (!state->needs_bind) {
pgf_parsing_lookahead(ps, state, pgf_parsing_lookahead(ps, state,
0, gu_seq_length(ps->concr->sequences)-1, 0, gu_seq_length(ps->concr->sequences)-1,
0, strlen(ps->sentence)-state->end_offset); 1, strlen(ps->sentence)-state->end_offset);
}
}
*pstate = state; *pstate = state;
@@ -1269,12 +1281,12 @@ pgf_parsing_td_predict(PgfParsing* ps,
pgf_parsing_production(ps, ps->before, conts, prod); pgf_parsing_production(ps, ps->before, conts, prod);
} }
if (!ps->before->needs_bind) {
// Bottom-up prediction for lexical and epsilon rules // Bottom-up prediction for lexical and epsilon rules
size_t n_idcs = gu_buf_length(ps->before->lexicon_idx); size_t n_idcs = gu_buf_length(ps->before->lexicon_idx);
for (size_t i = 0; i < n_idcs; i++) { for (size_t i = 0; i < n_idcs; i++) {
PgfLexiconIdxEntry* lentry = PgfLexiconIdxEntry* lentry =
gu_buf_index(ps->before->lexicon_idx, PgfLexiconIdxEntry, i); gu_buf_index(ps->before->lexicon_idx, PgfLexiconIdxEntry, i);
PgfProductionIdxEntry key; PgfProductionIdxEntry key;
key.ccat = ccat; key.ccat = ccat;
key.lin_idx = lin_idx; key.lin_idx = lin_idx;
@@ -1310,7 +1322,6 @@ pgf_parsing_td_predict(PgfParsing* ps,
} }
} }
} }
}
} else { } else {
/* If it has already been completed, combine. */ /* If it has already been completed, combine. */