1 %***************************************************************************%
2 %                                                                           %
3 %  Copyright (C) 2005, 2006 Sampo Pyysalo, Sophie Aubin                     %
4 %  Copyright (C) 2009, 2012 Linas Vepstas                                   %
5 %  See file "LICENSE" for information about commercial use of this system   %
6 %                                                                           %
7 %***************************************************************************%
8
9% This file contains regular expressions that are used to match
10% tokens not found in the dictionary. Each regex is given a name which
11% determines the disjuncts assigned when the regex matches; this name
12% must be defined in the dictionary along with the appropriate disjuncts.
13% Note that the order of the regular expressions matters: matches will
14% be attempted in the order in which the regexs appear in this file,
15% and only the first match will be used.
16%
17% Regex'es that are preceded by !, if they match a token, stop
18% further match tries of the same regex name. Thus, they can serve
19% as a kind of a negative look-ahead.
20
21% Numbers.
22% XXX, we need to add utf8 U+00A0 "no-break space"
23%
24% Allows at most two colons in hour-minute-second HH:MM:SS expressions
25% Allows at most two digits between colons
26<HMS-TIME>: /^[0-9][0-9]?(:[0-9][0-9]?(:[0-9][0-9]?)?)?$/
27
28% e.g. 1950's leading number can be higher, for science fiction.
29% Must be four digits, or possible three. Must end in s, 's ’s
30<DECADE-DATE>: /^([1-4][0-9][0-9]|[1-9][0-9])0(s|'s|’s)$/
31
32% Similar to above, but does not end in s. Only allows four digits.
33% We process this before NUMBERS below, so that this is matched first.
34<YEAR-DATE>: /^([1-4][0-9]{3}|[1-9][0-9]{0,2})$/
35
36% Day-of-month names; this regex will match before the one below.
37<DAY-ORDINALS>: /^(1st|2nd|3rd|[4-9]th|1[0-9]th|2(0th|1st|2nd|3rd|[4-9]th)|30th|31st)$/
38
39% Ordinal numbers; everything except 1st through 13th
40% is handled by regex.
41<ORDINALS>: /^[1-9][0-9]*(0th|1st|2nd|3rd|[4-9]th)$/
42
43% Allows any number of commas or periods
44% Be careful not match the period at the end of a sentence;
45% for example: "It happened in 1942."
46<NUMBERS>: /^[0-9,.]*[0-9]$/
47% This parses signed numbers and ranges, e.g. "-5" and "5-10" and "9+/-6.5"
48<NUMBERS>: /^[0-9.,-]*[0-9](\+\/-[0-9.,-]*[0-9])?$/
49% Parses simple fractions e.g. "1/60" with no decimal points or anything fancy
50<FRACTION>: /^[0-9]+\/[0-9]+$/
51% "10(3)" exponent (used in PubMed)
52<NUMBERS>: /^[0-9.,-]*[0-9][0-9.,-]*\([0-9:.,-]*[0-9][0-9.,-]*\)$/
53
54% Roman numerals
55% The first expr has the problem that it matches an empty string.  The
56% cure for this is to use look-ahead, but neither the Gnu nor the BSD
57% regex libs support look-ahead. I can't think of a better solution.
58<ROMAN-NUMERAL-WORDS>: /^M*(CM|D?C{0,3}|CD)(XC|L?X{0,3}|XL)(IX|V?I{0,3}|IV)$/
59% ROMAN-NUMERAL-WORDS: /^(?=(M|C|D|L|X|V|I)+)M*(CM|D?C{0,3}|CD)(XC|L?X{0,3}|XL)(IX|V?I{0,3}|IV)$/
60% ROMAN-NUMERAL-WORDS: /^(?=.+)M*(CM|D?C{0,3}|CD)(XC|L?X{0,3}|XL)(IX|V?I{0,3}|IV)$/
61
62% Strings of initials. e.g "Dr. J.G.D. Smith lives on Main St."
63% Make it at least two letters long, as otherwise it clobbers
64% single-letter handling in the dict, which is different.
65<INITIALS>: /^[A-Z]\.([A-Z]\.)+$/
66
67% Strings of two or more upper-case letters. These might be initials,
68% but are more likely to be titles (e.g. MD LLD JD) and might also
69% be part numbers (see below, PART-NUMBER:)
70<ALL-UPPER>: /^[A-Z]([A-Z])+$/
71
72% Greek letters with numbers
73<GREEK-LETTER-AND-NUMBER>: /^(alpha|beta|gamma|delta|epsilon|zeta|eta|theta|iota|kappa|lambda|mu|nu|xi|omicron|pi|rho|sigma|tau|upsilon|phi|chi|psi|omega)-?[0-9]+$/
74<PL-GREEK-LETTER-AND-NUMBER>: /^(alpha|beta|gamma|delta|epsilon|zeta|eta|theta|iota|kappa|lambda|mu|nu|xi|omicron|pi|rho|sigma|tau|upsilon|phi|chi|psi|omega)s-?[0-9]+$/
75
76% Some "safe" derived units. Simple units are in dictionary.
77% The idea here is for the regex to match something that is almost
78% certainly part of a derived unit, and allow the rest to be
79% anything; this way we can capture difficult derived units such
80% as "mg/kg/day" and even oddities such as "micrograms/mouse/day"
81% without listing them explicitly.
82% TODO: add more.
83% Some (real) misses from these:
84% micrograms.kg-1.h-1 microM-1 J/cm2 %/day mN/m cm/yr
85% m/s days/week ml/s degrees/sec cm/sec cm/s mm/s N/mm (is that a unit?)
86% cuts/minute clicks/s beats/minute x/week W/kg/W %/patient-year
87% microIU/ml degrees/s counts/mm2 cells/mm3 tumors/mouse
88% mm/sec ml/hr mJ/cm(2) m2/g amol/mm2 animals/group
89% h-1 min-1 day-1 cm-1 mg-1 kg-1 mg.m-2.min-1 ms.cm-1 g-1
90% sec-1 ms-1 ml.min.-1kg-1 ml.hr-1
91% also, both kilometer and kilometers seem to be absent(!)
92% remember "mm"!
93
94% grams/anything
95<UNITS>: /^([npmk]|milli|micro|nano|pico|femto|atto|kilo|mega|tera)?(g|grams?)\//
96
97% mol/anything
98<UNITS>: /^([fnmp]|milli|micro|nano|pico|femto|atto|mu)?mol(es)?\//
99
100% common endings
101<UNITS>: /^[a-zA-Z\/.]+\/((m|micro)?[lLg]|mg|kg|mol|min|day|h|hr)$/
102
103% common endings, except in the style "mg.kg-1" instead of "mg/kg".
104<UNITS>: /^[a-zA-Z\/.1-]+\.((m|micro)?[lLg]|mg|kg|mol|min|day|h|hr)(-1|\(-1\))$/
105
106% combinations of numbers and units, e.g. "50-kDa", "1-2h"
107% TODO: Clean up and check that these are up-to-date wrt the
108% dictionary-recognized units; this is quite a mess currently.
109% TODO: Extend the "number" part of the regex to allow anything
110% that the NUMBER regex matches.
111% One problem here is a failure to split up the expression ...
112% e.g. "2hr" becomes 2 - ND - hr with the ND link. But 2-hr is treated
113% as a single word ('I is a 2-hr wait')
114% NUMBER-AND-UNIT: /^[0-9.,-]+(msec|s|min|hour|h|hr|day|week|wk|month|year|yr|kDa|kilodalton|base|kilobase|base-pair|kD|kd|kDa|bp|nt|kb|mm|mg|cm|nm|g|Hz|ms|kg|ml|mL|km|microm|\%)$/
115% Comment out above, it screws up handling of unit suffixes, for
116% example: "Zangbert stock fell 30% to $2.50 yesterday."
117
118% fold-words. Matches NUMBER-fold, where NUMBER can be either numeric
119% or a spelled-out number, and the hyphen is optional. Note that for
120% spelled-out numbers, anything is allowed between the "initial" number
121% and "fold" to catch e.g. "two-to-three fold" ("fourteen" etc. are absent
122% as the prefix "four" is sufficient to match).
123<FOLD-WORDS>: /^[0-9.,:-]*[0-9]([0-9.,:-]|\([0-9.,:-]*[0-9][0-9.,:-]*\)|\+\/-)*-?fold$/
124<FOLD-WORDS>: /^(one|two|three|four|five|six|seven|eight|nine|ten|eleven|twelve|thirteen|fifteen|twenty|thirty|fifty|hundred|thousand|million).*fold$/
125
126% Plural proper nouns.
127% Make sure that apostrophe-s is split out correctly.
128<PL-CAPITALIZED-WORDS>:  /^[[:upper:]].*[^iuoys'’]s$/
129
130% Other proper nouns.
131% We demand that these end with an alphanumeric, i.e. explicitly
132% reject punctuation. We don't want this regex to "swallow" any trailing
133% commas, colons, or periods/question-marks at the end of sentences.
134% In addition, this must not swallow words ending in 's 'll etc.
135% (... any affix, for that matter ...) and so no embedded apostrophe
136<CAPITALIZED-WORDS>:     /^[[:upper:]][^'’]*[^[:punct:]]$/
137
138% SUFFIX GUESSING
139% For all suffix-guessing patterns, we insist that the pattern start
140% with an alphanumeric. This is needed to guarantee that the
141% prefix-stripping code works correctly, as otherwise, the regex will
142% gobble the prefix. So for example: "We left (carrying the dog) and
143% Fred followed."  Since "(carrying" is not in the dict, we need to be
144% sure to not match the leading paren so that it will get tripped.
145%
146<ING-WORDS>:        /^\w.+ing$/
147
148% Plurals or verb-s. Make sure that apostrophe-s is split out correctly.
149% e.g. "The subject's name is John Doe."  should be
150%     +--Ds--+---YS--+--Ds-+
151%     |      |       |     |
152%    the subject.n 's.p name.n
153<S-WORDS>:          /^\w.+[^iuoys'’]s$/
154
155% Verbs ending -ed.
156<ED-WORDS>:         /^\w.+ed$/
157
158% Advebs ending -ly.
159<LY-WORDS>:         /^\w.+ly$/
160
161% Nouns ending in -ism, -asm (chiliasm .. ) Usually mass nouns
162% Stubbed out for now; I'm not convinced this improves accuracy.
163% ISM-WORDS:        /^\w.+asm$/
164% ISM-WORDS:        /^\w.+ism$/
165
166% Corresponding count noun version of above (chiliast...)
167% AST-WORDS:        /^\w.+ast$/
168% AST-WORDS:        /^\w.+ist$/
169
170% Corresponding adjectival form of above
171<ADJ-WORDS>: /^\w.+astic$/
172<ADJ-WORDS>: /^\w.+istic$/
173
174% Nouns ending -ation  stubbed out in BioLG, stub out here ...
175%ATION-WORDS:      /^\w.+ation$/
176
177% Extension by LIPN 11/10/2005
178% nouns -- typically seen in (bio-)chemistry texts
179% synthetase, kinase
180% 5-(hydroxymethyl)-2’-deoxyuridine
181% hydroxyethyl, hydroxymethyl
182% septation, reguion
183% isomaltotetraose, isomaltotriose
184% glycosylphosphatidylinositol
185% iodide, oligodeoxynucleotide
186% chronicity, hypochromicity
187<MC-NOUN-WORDS>: /^\w.+ase$/
188<MC-NOUN-WORDS>: /^\w.+ene$/
189<MC-NOUN-WORDS>: /^\w.+ine?$/
190<MC-NOUN-WORDS>: /^\w.+yl$/
191<MC-NOUN-WORDS>: /^\w.+ion$/
192<MC-NOUN-WORDS>: /^\w.+ose$/
193<MC-NOUN-WORDS>: /^\w.+ol$/
194<MC-NOUN-WORDS>: /^\w.+ide$/
195<MC-NOUN-WORDS>: /^\w.+ity$/
196
197% Can take TOn+.  Must appear after above, to avoid clash with +ity
198<NOUN-TO-WORDS>: /^\w.+ty$/
199<NOUN-TO-WORDS>: /^\w.+cy$/
200<NOUN-TO-WORDS>: /^\w.+nce$/
201
202% replicon, intron
203<C-NOUN-WORDS>: /^\w.+o[rn]$/
204
205% adjectives
206% exogenous, heterologous
207% intermolecular, intramolecular
208% glycolytic, ribonucleic, uronic
209% ribosomal, ribsosomal
210% nonpermissive, thermosensitive
211% inducible, metastable
212<ADJ-WORDS>: /^\w.+ous$/
213<ADJ-WORDS>: /^\w.+ar$/
214<ADJ-WORDS>: /^\w.+ic$/
215<ADJ-WORDS>: /^\w.+al$/
216<ADJ-WORDS>: /^\w.+ive$/
217<ADJ-WORDS>: /^\w.+ble$/
218
219% Usually capitalized place names: Georgian, Norwegian
220<ADJ-WORDS>: /^\w.+ian$/
221
222% latin (postposed) adjectives
223% influenzae, tarentolae
224% pentosaceus, luteus, carnosus
225<LATIN-ADJ-WORDS>: /^\w.+ae$/
226<LATIN-ADJ-WORDS>: /^\w.+us$/ % must appear after -ous in this file
227
228% latin (postposed) adjectives  or latin plural noun
229% brevis, israelensis
230% japonicum, tabacum, xylinum
231<LATIN-ADJ-P-NOUN-WORDS>: /^\w.+is?$/
232<LATIN-ADJ-S-NOUN-WORDS>: /^\w.+um$/
233
234
235% Hyphenated words. In the original LG morpho-guessing system that
236% predated the regex-based system, hyphenated words were detected
237% before ING-WORDS, S-WORDS etc., causing e.g. "cross-linked" to be
238% treated as a HYPHENATED-WORD (a generic adjective/noun), and
239% never a verb. To return to this ordering, move this regex just
240% after the CAPITALIZED-WORDS regex.
241% We also match on commas, dots, brackets:
242% n-amino-3-azabicyclo[3.3.0]octane
243% 3'-Amino-2',3'-dideoxyguanosine
244% N-Phenylsulphonyl-N'-(3-azabicycloalkyl)
245% []...] means "match right-bracket"
246% Explicitly call out (5'|3') so that we don't all a generic match to 'll
247%  /^[[:alnum:]][][:alnum:],:.\[-]*-[][:alnum:],:.\[-]*[[:alnum:]]$/
248<HYPHENATED-WORDS>: !/--/
249<HYPHENATED-WORDS>: !/[[:punct:]]$/
250<HYPHENATED-WORDS>:
251  /^([[:alnum:]]|5'|3'|2'|N')([][:alnum:],:.()[-]|5'|3'|2'|N')*-[][:alnum:],:.()[-]*[[:alnum:]]*$/
252
253% Emoticon checks must come *after* the above, so that the above take precedence.
254% See Wikipedia List_of_emoticons (also the References section).
255%
256% Emoticons must be entirely made of punctuation, length 2 or longer ;)
257% XXX [:punct:] is strangely broken, I have to add ;-< explicitly
258% XXX: Don't use [:punct:].  Do NOT include period!!
259% XXX: The problem with below is that 5. 7. 8. get recognized as emoticons,
260% which then prevents splitting for list numbers.  (e.g "step 5. Do this.")
261%
262% Arghh. Other valid number expressions are clobbered by the emoticons.
263% For example: $5 $7 8%  The quick fix is to remove the numbers.
264% Other breakages: The below clobbers "Bob, who ..." because it
265% matches Bob, as an emoticon.
266%
267% EMOTICON: /^[[:punct:];BDOpTX0578Ｃ☆ಠ●＠◎～][[:punct:]<bcdDLmoOpPSTvX0358ಠっ○ 。゜✿☆＊レツ◕●≧∇≦□◇＠◎∩ω旦ヨ彡ミ‿◠￣ー～━-]+$/
268% EMOTICON: /^[!"#$%&'()*+,\-/:;<=>?@[\\\]^_`{|}~;BDOpTX0578Ｃ☆ಠ●＠◎～][!"#$%&'()*+,\-/:;<=>?@[\\\]^_`{|}~<bcdDLmoOpPSTvX0358ಠっ○ 。゜✿☆＊レツ◕●≧∇≦□◇＠◎∩ω旦ヨ彡ミ‿◠￣ー～━-]+$/
269<EMOTICON>: !/^"|[[:alnum:]]+"$/
270% "◠" is matched by [:punct:] using "libc" or "tre", but not using PCRE.
271% Hence it been added to the leading character subexpression. (Maybe
272% there are additional such characters.)
273<EMOTICON>: /^[[:punct:];BＣ☆ಠ●＠◎～◠][-!"#$%&'()+,:;<=>?@[\\^_`{|}~<cdDLmoOpPSTvXಠっ○ 。゜✿☆＊レツ◕●≧∇≦□◇＠◎∩ω旦ヨ彡ミ‿◠￣ー～━-]+$/
274
275% Part numbers should not match words with punctuation at their end.
276% Else sentences like "I saw him on January 21, 1990" have problems.
277% They should contain at least one number, and should not have dashes at their
278% start or end. A $ sign at the start is also too confusing.
279% The current regex system and the syntax of this file are not expressive enough
280% for things that should not be included. For example, we cannot prevent several
281% sequential "#" or dashes. It may match a word consisting of number+units, but
282% separate_word() will generate an alternative anyway.
283% The second part of this regex is for NNN-NNN in sentences like
284% "The plane is a 747-400".  However, such words currently match NUMBERS.
285<PART-NUMBER>:
286  /^[A-Z0-9#][A-Z0-9$\/#]*[A-Z0-9$\/#,.-]*[0-9][A-Z0-9$\/#,.-]*[A-Z0-9$\/#]+$|^[1-9][0-9]+[\/-][0-9+]$/
287
288% Single, stand-alone "quoted" "words" (so-called "scare" quotes).
289<QUOTED-WORD>: /^"[[:alnum:].-]+"$/
290
291% Sequence of punctuation marks. If some mark appears in the affix table
292% such as a period, comma, dash or underscore, and there's a sequence of
293% these, then treat it as a "fill-in-the-blank" placeholder.
294% This matters only for punc. appearing in the affix table, since the
295% tokenizer explicitly mangles based on these punctuation marks.
296%
297% Look for at least four in a row.
298<UNKNOWN-WORD>: /^[.,-]{4}[.,-]*$/
299