tommy/libpostal
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[fix] acronyms

Browse Source
This commit is contained in:
Al
2015-10-01 00:24:04 -04:00
parent 562aeb497d
commit 01856dd36d
2 changed files with 15358 additions and 15428 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30782
src/scanner.c
View File

File diff suppressed because it is too large Load Diff

4
src/scanner.re
View File

@@ -132,11 +132,11 @@ any_word = (({possible_word_char}*{letter}+{possible_word_char}*{non_breaking_da
// GB6, GB7 & GB8
hangul_syllable = (({hangul_syllable_class_L}(hangul_syllable_class_L|hangul_syllable_class_V|hangul_syllable_class_LV|hangul_syllable_class_LVT))|(({hangul_syllable_class_L}|{hangul_syllable_class_V})({hangul_syllable_class_V}{hangul_syllable_class_T}))|(({hangul_syllable_class_LVT}|{hangul_syllable_class_T}){hangul_syllable_class_T}));
apos_word = ("'"?({latinish_letter}+"'")+{latinish_letter}+"'"?);
apos_word = ("'"?({latinish_letter}+"'"){latinish_letter}+"'"?);
ellipsis = ("\."{2,}|"\u2026");
acronym = ({letter}"\.")+{letter}?;
acronym = ({letter}"\."){2,}{letter}?;
multi_punct_abbreviation = ({letter}+"\.")+{letter}?;
abbrev_word = (({letter}|{possible_word_char})+"\.")+({letter}|{possible_word_char}*);