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

[tokenization] Better scanner support for ideographic languages (Chinese, Japanese, Korean, etc.) with an IDEOGRAM token class in the scanner so we know when we're dealing with those languages vs. other random characters

Browse Source
This commit is contained in:
Al
2015-03-11 17:29:37 -04:00
parent 1dc0b8e07b
commit 94805fb1a7
2 changed files with 231822 additions and 250347 deletions
Download Patch File Download Diff File Expand all files Collapse all files

482163
src/scanner.c
View File

File diff suppressed because it is too large Load Diff

6
src/scanner.re
View File

@@ -75,12 +75,17 @@ mid_num_letter_chars = [\u002e\u2018\u2019\u2024\ufe52\uff07\uff0e];
numeric_chars = [\u0030-\u0039\u0660-\u0669\u066b\u06f0-\u06f9\u07c0-\u07c9\u0966-\u096f\u09e6-\u09ef\u0a66-\u0a6f\u0ae6-\u0aef\u0b66-\u0b6f\u0be6-\u0bef\u0c66-\u0c6f\u0ce6-\u0cef\u0d66-\u0d6f\u0de6-\u0def\u0e50-\u0e59\u0ed0-\u0ed9\u0f20-\u0f29\u1040-\u1049\u1090-\u1099\u17e0-\u17e9\u1810-\u1819\u1946-\u194f\u19d0-\u19d9\u1a80-\u1a89\u1a90-\u1a99\u1b50-\u1b59\u1bb0-\u1bb9\u1c40-\u1c49\u1c50-\u1c59\ua620-\ua629\ua8d0-\ua8d9\ua900-\ua909\ua9d0-\ua9d9\ua9f0-\ua9f9\uaa50-\uaa59\uabf0-\uabf9];
extend_num_letter_chars = [\u005f\u203f-\u2040\u2054\ufe33-\ufe34\ufe4d-\ufe4f\uff3f];
ideographic_numeric_chars = [\u00b2-\u00b3\u00b9\u00bc-\u00be\u2070\u2074-\u2079\u2080-\u2089\u2150-\u215f\u2189\u2460-\u249b\u24ea-\u24ff\u2776-\u2793\u3192-\u3195\u3220-\u3229\u3248-\u324f\u3251-\u325f\u3280-\u3289\u32b1-\u32bf\ua830-\ua835\u2160-\u2182\u2185-\u2188\u09f4-\u09f9\u0b72-\u0b77\u0bf0-\u0bf2\u0c78-\u0c7e\u0d70-\u0d75\u0f2a-\u0f33\u1369-\u137c\u16ee-\u16f0\u17f0-\u17f9\u3007\u3021-\u3029\u3038-\u303a\u2cfd\u19da\ua6e6-\ua6ef];
ideographic_chars = [\u0e01-\u0e30\u0e31\u0e32-\u0e33\u0e34-\u0e3a\u0e40-\u0e45\u0e46\u0e47-\u0e4e\u0e4f\u0e50-\u0e59\u0e5a-\u0e5b\u0e81-\u0e82\u0e84\u0e87-\u0e88\u0e8a\u0e8d\u0e94-\u0e97\u0e99-\u0e9f\u0ea1-\u0ea3\u0ea5\u0ea7\u0eaa-\u0eab\u0ead-\u0eb0\u0eb1\u0eb2-\u0eb3\u0eb4-\u0eb9\u0ebb-\u0ebc\u0ebd\u0ec0-\u0ec4\u0ec6\u0ec8-\u0ecd\u0ed0-\u0ed9\u0edc-\u0edf\u0f00\u0f01-\u0f03\u0f04-\u0f12\u0f13\u0f14\u0f15-\u0f17\u0f18-\u0f19\u0f1a-\u0f1f\u0f20-\u0f29\u0f2a-\u0f33\u0f34\u0f35\u0f36\u0f37\u0f38\u0f39\u0f3a\u0f3b\u0f3c\u0f3d\u0f3e-\u0f3f\u0f40-\u0f47\u0f49-\u0f6c\u0f71-\u0f7e\u0f7f\u0f80-\u0f84\u0f85\u0f86-\u0f87\u0f88-\u0f8c\u0f8d-\u0f97\u0f99-\u0fbc\u0fbe-\u0fc5\u0fc6\u0fc7-\u0fcc\u0fce-\u0fcf\u0fd0-\u0fd4\u0fd9-\u0fda\u1100-\u11ff\u302e-\u302f\u3131-\u318e\u3200-\u321e\u3260-\u327e\ua960-\ua97c\uac00-\ud7a3\ud7b0-\ud7c6\ud7cb-\ud7fb\uffa0-\uffbe\uffc2-\uffc7\uffca-\uffcf\uffd2-\uffd7\uffda-\uffdc\u3041-\u3096\u309d-\u309e\u309f\u2e80-\u2e99\u2e9b-\u2ef3\u2f00-\u2fd5\u3005\u3007\u3021-\u3029\u3038-\u303a\u303b\u3400-\u4db5\u4e00-\u9fcc\uf900-\ufa6d\ufa70-\ufad9\ua000-\ua014\ua015\ua016-\ua48c\ua490-\ua4c6\u1b00-\u1b03\u1b04\u1b05-\u1b33\u1b34\u1b35\u1b36-\u1b3a\u1b3b\u1b3c\u1b3d-\u1b41\u1b42\u1b43-\u1b44\u1b45-\u1b4b\u1b50-\u1b59\u1b5a-\u1b60\u1b61-\u1b6a\u1b6b-\u1b73\u1b74-\u1b7c\ua980-\ua982\ua983\ua984-\ua9b2\ua9b3\ua9b4-\ua9b5\ua9b6-\ua9b9\ua9ba-\ua9bb\ua9bc\ua9bd-\ua9c0\ua9c1-\ua9cd\ua9d0-\ua9d9\ua9de-\ua9df];
single_quote = [\u0027];
double_quote = [\u0022];
letter = {letter_lower_chars}|{letter_upper_chars}|{letter_title_chars}|{letter_other_alpha_chars}|{hebrew_letter_chars};
latinish_letter = {letter_lower_chars}|{letter_upper_chars}|{letter_title_chars};
ideographic_symbol = {ideographic_chars}|{ideographic_numeric_chars};
underscore = [_];
hyphen = [\-];
@@ -144,6 +149,7 @@ abbreviation = ({word})"\.";
{numeric} { return NUMERIC; }
{apos_word} { return WORD; }
{ideographic_symbol} { return IDEOGRAPH; }
{word} { return WORD; }
{katakana} { return WORD; }
{any_word} { return WORD; }