@chaffjs/lang-en 0.35.0 → 0.36.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (67) hide show
  1. package/dist/citation.d.ts.map +1 -1
  2. package/dist/citation.js +8 -2
  3. package/dist/citation.js.map +1 -1
  4. package/dist/names-read-as-verbs.d.ts +21 -0
  5. package/dist/names-read-as-verbs.d.ts.map +1 -0
  6. package/dist/names-read-as-verbs.js +40 -0
  7. package/dist/names-read-as-verbs.js.map +1 -0
  8. package/dist/pos.d.ts.map +1 -1
  9. package/dist/pos.js +30 -1
  10. package/dist/pos.js.map +1 -1
  11. package/dist/structure.d.ts.map +1 -1
  12. package/dist/structure.js +13 -0
  13. package/dist/structure.js.map +1 -1
  14. package/lexicons/ai-tell.yaml +61 -27
  15. package/lexicons/announcing-opener.yaml +7 -0
  16. package/lexicons/article-sound.yaml +1 -0
  17. package/lexicons/citation-series.yaml +1 -0
  18. package/lexicons/clause-conjunction.yaml +7 -0
  19. package/lexicons/closing-cliche.yaml +9 -0
  20. package/lexicons/closing-exhortation.yaml +11 -0
  21. package/lexicons/cold-open.yaml +30 -0
  22. package/lexicons/common-acronym.yaml +15 -0
  23. package/lexicons/comparative-baseline.yaml +14 -0
  24. package/lexicons/condition-heading.yaml +21 -0
  25. package/lexicons/connective-opener.yaml +23 -0
  26. package/lexicons/contraction-head.yaml +10 -0
  27. package/lexicons/contrast-amount.yaml +13 -0
  28. package/lexicons/contrast-lead.yaml +23 -0
  29. package/lexicons/contrast-turn.yaml +5 -0
  30. package/lexicons/drug-stem.yaml +48 -0
  31. package/lexicons/elision-mark.yaml +9 -0
  32. package/lexicons/email-closing.yaml +7 -1
  33. package/lexicons/email-salutation-end.yaml +7 -0
  34. package/lexicons/email-stock-courtesy.yaml +29 -0
  35. package/lexicons/everyday-name.yaml +24 -0
  36. package/lexicons/extra-word.yaml +15 -1
  37. package/lexicons/honorific.yaml +3 -0
  38. package/lexicons/indefinite-article.yaml +8 -0
  39. package/lexicons/intent-phrase.yaml +21 -0
  40. package/lexicons/interviewer-mark.yaml +10 -0
  41. package/lexicons/list-continues.yaml +9 -0
  42. package/lexicons/name-capitals-prefix.yaml +16 -0
  43. package/lexicons/name-direction-word.yaml +10 -0
  44. package/lexicons/name-title-head.yaml +23 -0
  45. package/lexicons/name-word-ending.yaml +10 -0
  46. package/lexicons/navigation-line.yaml +11 -0
  47. package/lexicons/open-list-end.yaml +10 -0
  48. package/lexicons/over-general-claim.yaml +57 -6
  49. package/lexicons/padded-intro.yaml +14 -0
  50. package/lexicons/product-name.yaml +9 -0
  51. package/lexicons/prohibition-opener.yaml +6 -0
  52. package/lexicons/superlative-goal.yaml +40 -0
  53. package/lexicons/superlative-part.yaml +22 -0
  54. package/lexicons/superlative-phrase.yaml +8 -0
  55. package/lexicons/superlative-purpose.yaml +7 -0
  56. package/lexicons/superlative-referent.yaml +15 -0
  57. package/lexicons/superlative-scope.yaml +5 -1
  58. package/lexicons/template-heading.yaml +35 -0
  59. package/lexicons/text-message-verb.yaml +11 -0
  60. package/lexicons/uninflected-word.yaml +22 -0
  61. package/lexicons/unprompted-denial.yaml +113 -0
  62. package/lexicons/word-suffix.yaml +29 -1
  63. package/package.json +1 -1
  64. package/src/citation.ts +9 -2
  65. package/src/names-read-as-verbs.ts +65 -0
  66. package/src/pos.ts +33 -1
  67. package/src/structure.ts +14 -0
@@ -58,10 +58,16 @@ entries:
58
58
  - pattern: WAV
59
59
  - pattern: MOV
60
60
  - pattern: SVG
61
+ # Office file formats, written without explanation in download lists (DOCX, 44 KB) as PDF and CSV are. DOC and PPT are other acronyms too, so they are left out.
62
+ - pattern: DOCX
63
+ - pattern: XLSX
64
+ - pattern: PPTX
65
+ - pattern: XLS
61
66
  - pattern: QR
62
67
  - pattern: GPS
63
68
  - pattern: SNS
64
69
  - pattern: TV
70
+ - pattern: BB # the gun and its shot (BB guns), an everyday word
65
71
  - pattern: KB
66
72
  - pattern: MB
67
73
  - pattern: GB
@@ -100,9 +106,18 @@ entries:
100
106
  - pattern: UV
101
107
  - pattern: FYI
102
108
  - pattern: LGBTQ
109
+ - pattern: CD
110
+ - pattern: ROM
111
+ - pattern: LED
112
+ - pattern: WIFI
113
+ - pattern: VIP
114
+ - pattern: RV
115
+ - pattern: TBA
116
+ - pattern: PTA
103
117
  # Names a reader knows as names, not as acronyms to spell out: the file every repository opens with, and a licence.
104
118
  - pattern: README
105
119
  - pattern: MIT
120
+ - pattern: BSD
106
121
  # & で繋いだ、仕事の文書で説明なしで通じる語。
107
122
  - pattern: Q&A
108
123
  - pattern: R&D
@@ -11,6 +11,14 @@
11
11
  # the words before it and compares nothing. Matched on the words up to the comparative, joined by spaces.
12
12
  # pointer: a word opening the sentence that points at the example just shown ("This is much better!"); right after two
13
13
  # code examples, the baseline is the first one.
14
+ # cause: a word after another word and before the comparative that sets the clause before it against the comparison
15
+ # ("Print statements work, but a real debugger is better"); that clause is the baseline.
16
+ # opener: a word opening the sentence that puts the comparison after a change or a topic it names ("As the application
17
+ # divides into services, the project can move faster"; "By pairing the data with research, …"; "As to the codes, the
18
+ # question is more fundamental"). The baseline is the state before that change, or the topic before.
19
+ # aim: a verb shortly before the comparative that makes it a change from the present ("to make results more
20
+ # predictable", "We can do better"). The baseline is the present state, as in Japanese より良くする.
21
+ # A baseline of several words ("that follows") is matched on the words joined by a space.
14
22
  id: comparative-baseline
15
23
  language: en
16
24
  entries:
@@ -39,6 +47,12 @@ entries:
39
47
  - { pattern: versus, group: baseline }
40
48
  - { pattern: vs, group: baseline }
41
49
  - { pattern: whereas, group: baseline }
50
+ - { pattern: that follows, group: baseline }
51
+ - { pattern: but, group: cause }
52
+ - { pattern: as, group: opener }
53
+ - { pattern: by, group: opener }
54
+ - { pattern: make, group: aim }
55
+ - { pattern: do, group: aim }
42
56
  - { pattern: even, group: beyond }
43
57
  - { pattern: still, group: beyond }
44
58
  - { pattern: if, group: condition }
@@ -0,0 +1,21 @@
1
+ # Headings of a section that lists conditions (what a candidate must have, what a role does, who may apply) rather than
2
+ # claims. "Experience with Docker" or "Dependency updates" states a condition; no figure is missing from it.
3
+ # concrete-evidence-density does not check such a section. Compared with the whole heading, in lower case, without a
4
+ # trailing colon.
5
+ id: condition-heading
6
+ language: en
7
+ entries:
8
+ - pattern: requirements
9
+ - pattern: minimum requirements
10
+ - pattern: qualifications
11
+ - pattern: minimum qualifications
12
+ - pattern: preferred qualifications
13
+ - pattern: required qualifications
14
+ - pattern: responsibilities
15
+ - pattern: key responsibilities
16
+ - pattern: duties
17
+ - pattern: nice-to-haves
18
+ - pattern: nice to have
19
+ - pattern: nice to haves
20
+ - pattern: eligibility
21
+ - pattern: who can apply
@@ -0,0 +1,23 @@
1
+ # Words that open a sentence and tie it to the one before ("However, even more important is …"). Followed by a comma at
2
+ # the head of a sentence they are an introduction, not the first item of a list. Read by oxford-comma-consistency.
3
+ id: connective-opener
4
+ language: en
5
+ entries:
6
+ - pattern: however
7
+ - pattern: therefore
8
+ - pattern: thus
9
+ - pattern: hence
10
+ - pattern: moreover
11
+ - pattern: furthermore
12
+ - pattern: additionally
13
+ - pattern: also
14
+ - pattern: meanwhile
15
+ - pattern: nevertheless
16
+ - pattern: nonetheless
17
+ - pattern: instead
18
+ - pattern: otherwise
19
+ - pattern: consequently
20
+ - pattern: indeed
21
+ - pattern: likewise
22
+ - pattern: similarly
23
+ - pattern: still
@@ -0,0 +1,10 @@
1
+ # The first halves the tagger splits off a negative contraction: ai|n't, ca|n't, wo|n't, sha|n't. The tagger's
2
+ # vocabulary holds them as a verb or a modal, so it reads them so everywhere, and "AI" (ai), "CA" (ca) become "be" and
3
+ # "can". Without "n't" right after, they are not the contraction, and the adapter reads them as names.
4
+ id: contraction-head
5
+ language: en
6
+ entries:
7
+ - pattern: ai
8
+ - pattern: ca
9
+ - pattern: wo
10
+ - pattern: sha
@@ -0,0 +1,13 @@
1
+ # Words that, right after a contrast frame, make it say an amount ("not just one coffee": more than one), not knock down
2
+ # an X nobody said. Position after: the word stands after the frame. A numeral (not just 2 rolls) is an amount anyway.
3
+ id: contrast-amount
4
+ language: en
5
+ entries:
6
+ - { pattern: one, position: after }
7
+ - { pattern: once, position: after }
8
+ - { pattern: two, position: after }
9
+ - { pattern: twice, position: after }
10
+ - { pattern: three, position: after }
11
+ - { pattern: a few, position: after }
12
+ - { pattern: a couple, position: after }
13
+ - { pattern: a single, position: after }
@@ -1,4 +1,7 @@
1
1
  # A denial that frames a contrast only when a turn (contrast-turn) answers it: "It's not a perk. It's a necessity."
2
+ # Group across: a bare denial that frames a contrast only when the next sentence opens with an across turn (It, They)
3
+ # and denies nothing ("What surprised me wasn't the food. It was the evenings."); a turn later in the same sentence,
4
+ # a concession ("I don't always. But ...") or a remark on the whole sentence ("That's more than ...") does not answer it.
2
5
  id: contrast-lead
3
6
  language: en
4
7
  entries:
@@ -13,3 +16,23 @@ entries:
13
16
  - pattern: they aren't
14
17
  - pattern: isn't about
15
18
  - pattern: is not about
19
+ - pattern: not really about
20
+ - pattern: isn't really about
21
+ - pattern: wasn't about
22
+ - pattern: wasn't really about
23
+ - pattern: isn't
24
+ group: across
25
+ - pattern: wasn't
26
+ group: across
27
+ - pattern: aren't
28
+ group: across
29
+ - pattern: weren't
30
+ group: across
31
+ - pattern: don't
32
+ group: across
33
+ - pattern: doesn't
34
+ group: across
35
+ - pattern: didn't
36
+ group: across
37
+ - pattern: not because
38
+ group: across
@@ -1,4 +1,5 @@
1
1
  # What answers a denial (contrast-lead): later in the same sentence, or opening the next one.
2
+ # Group across: a subject that answers only by opening the next sentence ("They come for the table."), never inside one.
2
3
  id: contrast-turn
3
4
  language: en
4
5
  entries:
@@ -9,3 +10,7 @@ entries:
9
10
  - pattern: they're
10
11
  - pattern: they are
11
12
  - pattern: but
13
+ - pattern: it
14
+ group: across
15
+ - pattern: they
16
+ group: across
@@ -0,0 +1,48 @@
1
+ # Stems of drugs' international non-proprietary names (the WHO's INN stems): a word ending in one is a drug's name
2
+ # (paroxetine by -oxetine, as fluoxetine; valsartan by -sartan), not a slip. unknown-word does not report such a word
3
+ # when at least three letters stand before the stem. Only stems no ordinary English word ends in are listed.
4
+ id: drug-stem
5
+ language: en
6
+ entries:
7
+ - pattern: afil
8
+ - pattern: azepam
9
+ - pattern: azepine
10
+ - pattern: azolam
11
+ - pattern: azoline
12
+ - pattern: azosin
13
+ - pattern: barbital
14
+ - pattern: caine
15
+ - pattern: ciclovir
16
+ - pattern: cillin
17
+ - pattern: conazole
18
+ - pattern: cycline
19
+ - pattern: dipine
20
+ - pattern: dronate
21
+ - pattern: floxacin
22
+ - pattern: gliflozin
23
+ - pattern: gliptin
24
+ - pattern: glutide
25
+ - pattern: lukast
26
+ - pattern: mycin
27
+ - pattern: navir
28
+ - pattern: olol
29
+ - pattern: oxetine
30
+ - pattern: parin
31
+ - pattern: peridol
32
+ - pattern: pramine
33
+ - pattern: prazole
34
+ - pattern: previr
35
+ - pattern: profen
36
+ - pattern: sartan
37
+ - pattern: semide
38
+ - pattern: setron
39
+ - pattern: tadine
40
+ - pattern: tegravir
41
+ - pattern: thiazide
42
+ - pattern: tidine
43
+ - pattern: tinib
44
+ - pattern: triptan
45
+ - pattern: triptyline
46
+ - pattern: umab
47
+ - pattern: vastatin
48
+ - pattern: ximab
@@ -0,0 +1,9 @@
1
+ # Marks of an omission inside a quotation. A quotation that marks what it leaves out is an excerpt of another text (a
2
+ # statute, a ruling), so the commas of a list inside it are that text's, not the writer's ("words of the Fifth Amendment
3
+ # that 'No person shall be * * * deprived of life, liberty, or property'"). Read by oxford-comma-consistency.
4
+ id: elision-mark
5
+ language: en
6
+ entries:
7
+ - pattern: "..."
8
+ - pattern: "…"
9
+ - pattern: "* * *"
@@ -1,5 +1,7 @@
1
1
  # The closing a work email or letter ends with, before the writer's name. One of the last lines of the body (the name,
2
- # title and contact lines included) opening with one of these is a closing; case does not matter.
2
+ # title and contact lines included) opening with one of these, or one of its later sentences opening with one, is a
3
+ # closing; case does not matter. Between colleagues an email ends on a farewell (See you there) or on the apology it is
4
+ # written for (Sorry again for the wasted morning).
3
5
  id: email-closing
4
6
  language: en
5
7
  entries:
@@ -26,3 +28,7 @@ entries:
26
28
  - pattern: Take care
27
29
  - pattern: Looking forward
28
30
  - pattern: I look forward
31
+ - pattern: See you
32
+ - pattern: Talk soon
33
+ - pattern: Sorry again
34
+ - pattern: Apologies again
@@ -0,0 +1,7 @@
1
+ # The mark a name alone ends with when it is the salutation (Priya,). An internal email often opens on the reader's name
2
+ # and a comma, with no Dear or Hi; a first line of a few words ending with this mark is a greeting. Japanese has none: a
3
+ # name alone there (中村さん) is the addressee, and the greeting still follows it.
4
+ id: email-salutation-end
5
+ language: en
6
+ entries:
7
+ - pattern: ","
@@ -0,0 +1,29 @@
1
+ # Stock courtesies of a business email. One is ordinary politeness; a stack of them in one short email is what a
2
+ # reader notices. Counted per sentence. Only email-like forms: "reach out" and "if you have any questions" are left
3
+ # out, human reports and job notices in the corpus use them.
4
+ id: email-stock-courtesy
5
+ language: en
6
+ entries:
7
+ - pattern: hope you're having a good week
8
+ - pattern: hope you're having a great week
9
+ - pattern: hope you are having a good week
10
+ - pattern: hope you are having a great week
11
+ - pattern: hope you're having a good day
12
+ - pattern: hope you're having a great day
13
+ - pattern: hope this email finds you well
14
+ - pattern: hope this message finds you well
15
+ - pattern: hope this finds you well
16
+ - pattern: apologize for any inconvenience
17
+ - pattern: apologise for any inconvenience
18
+ - pattern: apologies for any inconvenience
19
+ - pattern: appreciate your flexibility
20
+ - pattern: appreciate your patience
21
+ - pattern: appreciate your understanding
22
+ - pattern: feel free to
23
+ - pattern: happy to discuss
24
+ - pattern: happy to talk it through
25
+ - pattern: happy to answer any questions
26
+ - pattern: please don't hesitate
27
+ - pattern: please do not hesitate
28
+ - pattern: let me know what works best
29
+ - pattern: do my best to accommodate
@@ -0,0 +1,24 @@
1
+ # Names every reader already knows: the months and the days of the week. Read by proper-noun-density, which does not count
2
+ # them: a date (April 17, 2026) is no name a newcomer has to look up. Matched as written, capital first.
3
+ id: everyday-name
4
+ language: en
5
+ entries:
6
+ - pattern: January
7
+ - pattern: February
8
+ - pattern: March
9
+ - pattern: April
10
+ - pattern: May
11
+ - pattern: June
12
+ - pattern: July
13
+ - pattern: August
14
+ - pattern: September
15
+ - pattern: October
16
+ - pattern: November
17
+ - pattern: December
18
+ - pattern: Monday
19
+ - pattern: Tuesday
20
+ - pattern: Wednesday
21
+ - pattern: Thursday
22
+ - pattern: Friday
23
+ - pattern: Saturday
24
+ - pattern: Sunday
@@ -1,7 +1,8 @@
1
1
  # Words in everyday technical and business writing that WordNet does not list. unknown-word reads them as known, with
2
2
  # their endings: function words WordNet leaves out (cannot, wherein, albeit, whilst), Latin phrases in English text
3
3
  # (a priori, in forma pauperis, de minimis), the legal words of contracts (thereunder, herefrom, monies, pendency,
4
- # cedent, telecopy) and newer coinages (onboard, roadmap, phishing, vishing, ransomware). A team adds its own words
4
+ # cedent, telecopy), newer coinages (onboard, roadmap, phishing, vishing, ransomware, agentic, toolbar) and everyday
5
+ # words WordNet missed (amidst, ahold, barista, grift). A team adds its own words
5
6
  # under names in chaff.yaml; this list is only for words any document may use.
6
7
  id: extra-word
7
8
  language: en
@@ -10,9 +11,12 @@ entries:
10
11
  - pattern: accessibility
11
12
  - pattern: admin
12
13
  - pattern: adware
14
+ - pattern: agentic
15
+ - pattern: ahold
13
16
  - pattern: albeit
14
17
  - pattern: alia
15
18
  - pattern: alterius
19
+ - pattern: amidst
16
20
  - pattern: amotion
17
21
  - pattern: api
18
22
  - pattern: app
@@ -23,6 +27,7 @@ entries:
23
27
  - pattern: backend
24
28
  - pattern: backlog
25
29
  - pattern: backslash
30
+ - pattern: barista
26
31
  - pattern: biometric
27
32
  - pattern: blog
28
33
  - pattern: bona
@@ -63,8 +68,10 @@ entries:
63
68
  - pattern: devops
64
69
  - pattern: dialog
65
70
  - pattern: distributee
71
+ - pattern: distro
66
72
  - pattern: dogfood
67
73
  - pattern: doozy
74
+ - pattern: dox
68
75
  - pattern: dropdown
69
76
  - pattern: ebook
70
77
  - pattern: ecommerce
@@ -90,6 +97,7 @@ entries:
90
97
  - pattern: generis
91
98
  - pattern: geospatial
92
99
  - pattern: github
100
+ - pattern: grift
93
101
  - pattern: hardcode
94
102
  - pattern: hardcoded
95
103
  - pattern: hashtag
@@ -115,6 +123,7 @@ entries:
115
123
  - pattern: interoperable
116
124
  - pattern: json
117
125
  - pattern: keylogger
126
+ - pattern: lakehouse
118
127
  - pattern: lest
119
128
  - pattern: licensor
120
129
  - pattern: lifecycle
@@ -129,11 +138,13 @@ entries:
129
138
  - pattern: metadata
130
139
  - pattern: middleware
131
140
  - pattern: minimis
141
+ - pattern: mockup
132
142
  - pattern: modulo
133
143
  - pattern: monies
134
144
  - pattern: multi
135
145
  - pattern: multiplet
136
146
  - pattern: mutex
147
+ - pattern: mythos
137
148
  - pattern: namespace
138
149
  - pattern: npm
139
150
  - pattern: obligee
@@ -203,6 +214,7 @@ entries:
203
214
  - pattern: sublicensee
204
215
  - pattern: subproject
205
216
  - pattern: sustainably
217
+ - pattern: synch
206
218
  - pattern: syntax
207
219
  - pattern: tanto
208
220
  - pattern: telecopy
@@ -213,6 +225,7 @@ entries:
213
225
  - pattern: timeline
214
226
  - pattern: timestamp
215
227
  - pattern: timezone
228
+ - pattern: toolbar
216
229
  - pattern: toolchain
217
230
  - pattern: toolkit
218
231
  - pattern: tooltip
@@ -221,6 +234,7 @@ entries:
221
234
  - pattern: tuple
222
235
  - pattern: typo
223
236
  - pattern: unius
237
+ - pattern: upsert
224
238
  - pattern: upskill
225
239
  - pattern: upwelling
226
240
  - pattern: url
@@ -13,3 +13,6 @@ entries:
13
13
  - pattern: "Dr"
14
14
  - pattern: "Miss"
15
15
  - pattern: "Madam"
16
+ # A law report prints an English judge's name in capitals after his title (Lord HOLT, Mr. Justice BULLER).
17
+ - pattern: "Lord"
18
+ - pattern: "Justice"
@@ -0,0 +1,8 @@
1
+ # The indefinite articles. "a simple" or "a flexible" with nothing after the adjective cannot stand as an item: the
2
+ # adjective waits for the noun after the comma or the and ("A simple, minimalist palette" / "Neat, a flexible and
3
+ # lightweight Sass grid"). "the disabled" can (the disabled, elderly residents, and veterans). Read by oxford-comma-consistency.
4
+ id: indefinite-article
5
+ language: en
6
+ entries:
7
+ - pattern: a
8
+ - pattern: an
@@ -0,0 +1,21 @@
1
+ # Words that make a sentence state a possibility, an obligation or the writer's own plan rather than a fact (Team members
2
+ # may continue; We will migrate; We recommend approving). A risk, a mitigation or a recommendation is written this way and
3
+ # asks for no figure behind it. concrete-evidence-density does not count such a sentence as a claim. Matched as whole
4
+ # words in lower case anywhere in the sentence. "will" counts only after "we": "This will save time" is a claim.
5
+ id: intent-phrase
6
+ language: en
7
+ entries:
8
+ - pattern: may
9
+ - pattern: might
10
+ - pattern: would
11
+ - pattern: should
12
+ - pattern: must
13
+ - pattern: ought to
14
+ - pattern: need to
15
+ - pattern: needs to
16
+ - pattern: we will
17
+ - pattern: we'll
18
+ - pattern: we shall
19
+ - pattern: we recommend
20
+ - pattern: we propose
21
+ - pattern: we suggest
@@ -0,0 +1,10 @@
1
+ # Marks that open an interviewer's line (Q: How did you start?), read only at the start of a paragraph.
2
+ # section-length-uniformity takes a document where at least half of the headed sections open with such a question as
3
+ # an interview, and does not compare its section lengths: each section is one question and its answer, so even lengths
4
+ # are the form. A bare Q also starts words (QR codes), so only the forms with a separator are listed.
5
+ id: interviewer-mark
6
+ language: en
7
+ entries:
8
+ - pattern: "Q:"
9
+ - pattern: "Q."
10
+ - pattern: "Interviewer:"
@@ -0,0 +1,9 @@
1
+ # Words opening the line just below a list that say it goes on beyond the items written ("etc.", "and so on").
2
+ # rule-of-three does not count a list followed by one as having exactly three items.
3
+ id: list-continues
4
+ language: en
5
+ entries:
6
+ - pattern: etc.
7
+ - pattern: and so on
8
+ - pattern: and more
9
+ - pattern: and others
@@ -0,0 +1,16 @@
1
+ # Surname prefixes a roster keeps in small letters when it sets a name in capitals: the Congressional Record writes
2
+ # McCaul as McCAUL and DesJarlais as DesJARLAIS. name-variant reads a name whose every word is in capitals, or in three or
3
+ # more capitals after one of these, as set in capitals, and leaves it out as it leaves ACME INC. Matched as written, at the
4
+ # start of a word.
5
+ id: name-capitals-prefix
6
+ language: en
7
+ entries:
8
+ - pattern: Mc
9
+ - pattern: Mac
10
+ - pattern: De
11
+ - pattern: Des
12
+ - pattern: Del
13
+ - pattern: Di
14
+ - pattern: Du
15
+ - pattern: La
16
+ - pattern: Le
@@ -0,0 +1,10 @@
1
+ # Words that point from one thing to another. Two names with the same two sides in the two orders around one of these
2
+ # ("ASCII to binary" and "binary to ASCII") are a direction and its inverse, not one name in two orders (name-variant).
3
+ # A word in letters is matched between spaces.
4
+ id: name-direction-word
5
+ language: en
6
+ entries:
7
+ - pattern: to
8
+ - pattern: into
9
+ - pattern: →
10
+ - pattern: "->"
@@ -0,0 +1,23 @@
1
+ # The last word of the title of a law or a body (the National Industrial Recovery Act, the Federal Trade Commission).
2
+ # name-variant reads three or more capitalised words ending in one of these as a title, and reports a title written once
3
+ # that is a repeated title with one word one letter away ("National Industrial Recover Act"). Matched as written.
4
+ id: name-title-head
5
+ language: en
6
+ entries:
7
+ - pattern: Act
8
+ - pattern: Code
9
+ - pattern: Statute
10
+ - pattern: Treaty
11
+ - pattern: Convention
12
+ - pattern: Regulation
13
+ - pattern: Directive
14
+ - pattern: Commission
15
+ - pattern: Administration
16
+ - pattern: Agency
17
+ - pattern: Authority
18
+ - pattern: Board
19
+ - pattern: Bureau
20
+ - pattern: Committee
21
+ - pattern: Council
22
+ - pattern: Department
23
+ - pattern: Office
@@ -0,0 +1,10 @@
1
+ # Last letters that make another form of a word in place of another (pattern in place of instead_of): the people of a
2
+ # place (Texan for Texas, Kansan for Kansas) and a Latin case beside the English plural (Romano beside Romans). name-variant
3
+ # does not read two one-word names that differ only in such a last letter as one name written two ways.
4
+ id: name-word-ending
5
+ language: en
6
+ entries:
7
+ - pattern: n
8
+ instead_of: s
9
+ - pattern: o
10
+ instead_of: s
@@ -0,0 +1,11 @@
1
+ # Site navigation that a web page keeps when it is converted to a document (Skip to main content, Back to top). It is
2
+ # not the document's prose, so concrete-evidence-density does not count it among a section's sentences. Compared with
3
+ # the whole sentence, in lower case, without its closing full stop.
4
+ id: navigation-line
5
+ language: en
6
+ entries:
7
+ - pattern: skip to main content
8
+ - pattern: skip to content
9
+ - pattern: skip navigation
10
+ - pattern: back to top
11
+ - pattern: return to top
@@ -0,0 +1,10 @@
1
+ # Words that stand for the rest of a list after its last and / or ("the number and type of rooms, and so forth"). The
2
+ # list goes on to them, so an and / or in the item before is inside that item. Read by oxford-comma-consistency.
3
+ id: open-list-end
4
+ language: en
5
+ entries:
6
+ - pattern: so forth
7
+ - pattern: so on
8
+ - pattern: the like
9
+ - pattern: the rest
10
+ - pattern: etc
@@ -1,11 +1,62 @@
1
1
  # Sweeping claims about people in general: what most people do, what nobody does. Read by over-general-claim, which
2
2
  # counts them per length of the document; one is ordinary. "Most people agree" and "everyone knows" are weasel-word's.
3
+ #
4
+ # general: names people at large, always counted.
5
+ # subject: counted only as the subject of a verb (many people keep ...), not as a count of people (see many people).
6
+ # who: counted unless the text says which people it means (bounded): a group named in the same or the previous
7
+ # sentence (group-noun, addressee), a word right after it (right-after: everyone here), or a past-tense verb
8
+ # right after it, which reports what one group did once (nobody caught it, everyone who jumped in).
9
+ # present-form: the present forms of be, have and do; the past-tense check reads them as present.
10
+ # relative: the pronoun the past-tense check steps over (everyone who jumped in).
3
11
  id: over-general-claim
4
12
  language: en
5
13
  entries:
6
- - pattern: most people
7
- - pattern: for most of us
8
- - pattern: for most households
9
- - pattern: nobody
10
- - pattern: everyone
11
- - pattern: anyone who
14
+ - { pattern: most people, group: general }
15
+ - { pattern: most of us, group: general }
16
+ - { pattern: for most households, group: general }
17
+ - { pattern: many people, group: subject }
18
+ - { pattern: nobody, group: who }
19
+ - { pattern: everyone, group: who }
20
+ - { pattern: anyone who, group: who }
21
+
22
+ - { pattern: team, group: group-noun }
23
+ - { pattern: teams, group: group-noun }
24
+ - { pattern: family, group: group-noun }
25
+ - { pattern: families, group: group-noun }
26
+ - { pattern: household, group: group-noun }
27
+ - { pattern: members, group: group-noun }
28
+ - { pattern: staff, group: group-noun }
29
+ - { pattern: colleagues, group: group-noun }
30
+ - { pattern: coworkers, group: group-noun }
31
+ - { pattern: co-workers, group: group-noun }
32
+ - { pattern: employees, group: group-noun }
33
+ - { pattern: crew, group: group-noun }
34
+ - { pattern: class, group: group-noun }
35
+ - { pattern: committee, group: group-noun }
36
+ - { pattern: department, group: group-noun }
37
+ - { pattern: office, group: group-noun }
38
+ - { pattern: guests, group: group-noun }
39
+ - { pattern: attendees, group: group-noun }
40
+ - { pattern: participants, group: group-noun }
41
+ - { pattern: call, group: group-noun }
42
+ - { pattern: meeting, group: group-noun }
43
+ - { pattern: room, group: group-noun }
44
+
45
+ - { pattern: all of you, group: addressee }
46
+ - { pattern: you all, group: addressee }
47
+
48
+ - { pattern: here, group: right-after }
49
+ - { pattern: present, group: right-after }
50
+
51
+ - { pattern: is, group: present-form }
52
+ - { pattern: are, group: present-form }
53
+ - { pattern: am, group: present-form }
54
+ - { pattern: has, group: present-form }
55
+ - { pattern: does, group: present-form }
56
+ - { pattern: "'s", group: present-form }
57
+ - { pattern: "'re", group: present-form }
58
+ - { pattern: "'m", group: present-form }
59
+ - { pattern: "'ve", group: present-form }
60
+
61
+ - { pattern: who, group: relative }
62
+ - { pattern: that, group: relative }
@@ -6,3 +6,17 @@ entries:
6
6
  - pattern: has gained significant attention
7
7
  - pattern: is becoming increasingly important
8
8
  - pattern: have you ever wondered
9
+ # A problem every team or company could name, used as the way in.
10
+ - pattern: many teams struggle
11
+ - pattern: many organizations struggle
12
+ - pattern: many organisations struggle
13
+ - pattern: many companies struggle
14
+ - pattern: many businesses struggle
15
+ - pattern: as organizations increasingly
16
+ - pattern: as organisations increasingly
17
+ - pattern: as businesses increasingly
18
+ - pattern: as companies increasingly
19
+ - pattern: in today's digital
20
+ - pattern: in today's world
21
+ - pattern: in an ever-changing
22
+ - pattern: it's no secret