@chaffjs/lang-en 0.34.0 → 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.
- package/dist/citation.d.ts +5 -0
- package/dist/citation.d.ts.map +1 -1
- package/dist/citation.js +29 -3
- package/dist/citation.js.map +1 -1
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +6 -1
- package/dist/index.js.map +1 -1
- package/dist/initial-stop.d.ts +27 -0
- package/dist/initial-stop.d.ts.map +1 -0
- package/dist/initial-stop.js +47 -0
- package/dist/initial-stop.js.map +1 -0
- package/dist/item-style.d.ts +5 -2
- package/dist/item-style.d.ts.map +1 -1
- package/dist/item-style.js +31 -6
- package/dist/item-style.js.map +1 -1
- package/dist/law-citation.d.ts +14 -0
- package/dist/law-citation.d.ts.map +1 -0
- package/dist/law-citation.js +58 -0
- package/dist/law-citation.js.map +1 -0
- package/dist/lead-initial.d.ts +5 -0
- package/dist/lead-initial.d.ts.map +1 -0
- package/dist/lead-initial.js +24 -0
- package/dist/lead-initial.js.map +1 -0
- package/dist/names-read-as-verbs.d.ts +21 -0
- package/dist/names-read-as-verbs.d.ts.map +1 -0
- package/dist/names-read-as-verbs.js +40 -0
- package/dist/names-read-as-verbs.js.map +1 -0
- package/dist/pos.d.ts.map +1 -1
- package/dist/pos.js +30 -1
- package/dist/pos.js.map +1 -1
- package/dist/structure.d.ts.map +1 -1
- package/dist/structure.js +67 -9
- package/dist/structure.js.map +1 -1
- package/lexicons/abbreviated-label.yaml +2 -0
- package/lexicons/ai-tell.yaml +61 -27
- package/lexicons/alternative-clause-label.yaml +6 -0
- package/lexicons/announcing-opener.yaml +7 -0
- package/lexicons/article-sound.yaml +1 -0
- package/lexicons/capital-phrase.yaml +3 -1
- package/lexicons/case-party-joiner.yaml +7 -0
- package/lexicons/citation-name-connector.yaml +28 -0
- package/lexicons/citation-series.yaml +5 -1
- package/lexicons/clause-conjunction.yaml +7 -0
- package/lexicons/closing-cliche.yaml +9 -0
- package/lexicons/closing-exhortation.yaml +11 -0
- package/lexicons/cold-open.yaml +30 -0
- package/lexicons/common-acronym.yaml +21 -1
- package/lexicons/comparative-baseline.yaml +27 -0
- package/lexicons/condition-heading.yaml +21 -0
- package/lexicons/conjunction-lookalike.yaml +13 -0
- package/lexicons/connective-opener.yaml +23 -0
- package/lexicons/contraction-head.yaml +10 -0
- package/lexicons/contrast-amount.yaml +13 -0
- package/lexicons/contrast-lead.yaml +23 -0
- package/lexicons/contrast-turn.yaml +5 -0
- package/lexicons/definition-scope-lead.yaml +11 -0
- package/lexicons/determiner-after-article.yaml +14 -0
- package/lexicons/drug-stem.yaml +48 -0
- package/lexicons/elision-mark.yaml +9 -0
- package/lexicons/email-closing.yaml +7 -1
- package/lexicons/email-salutation-end.yaml +7 -0
- package/lexicons/email-stock-courtesy.yaml +29 -0
- package/lexicons/enclosing-unit.yaml +14 -0
- package/lexicons/everyday-name.yaml +24 -0
- package/lexicons/extra-word.yaml +28 -1
- package/lexicons/figure-label-plural.yaml +19 -0
- package/lexicons/figure-number-joiner.yaml +20 -0
- package/lexicons/headnote-heading.yaml +8 -0
- package/lexicons/honorific.yaml +3 -0
- package/lexicons/indefinite-article.yaml +8 -0
- package/lexicons/initial-lead-word.yaml +7 -0
- package/lexicons/intent-phrase.yaml +21 -0
- package/lexicons/interviewer-mark.yaml +10 -0
- package/lexicons/link-label-ending.yaml +6 -0
- package/lexicons/list-conjunction.yaml +7 -0
- package/lexicons/list-continues.yaml +9 -0
- package/lexicons/name-abbreviation.yaml +21 -0
- package/lexicons/name-capitals-prefix.yaml +16 -0
- package/lexicons/name-direction-word.yaml +10 -0
- package/lexicons/name-title-head.yaml +23 -0
- package/lexicons/name-word-ending.yaml +10 -0
- package/lexicons/navigation-line.yaml +11 -0
- package/lexicons/newsletter-issue.yaml +9 -0
- package/lexicons/numbered-division.yaml +4 -1
- package/lexicons/open-list-end.yaml +10 -0
- package/lexicons/over-general-claim.yaml +62 -0
- package/lexicons/padded-intro.yaml +14 -0
- package/lexicons/placeholder-division.yaml +7 -0
- package/lexicons/prepositive-abbreviation.yaml +10 -0
- package/lexicons/product-name.yaml +9 -0
- package/lexicons/prohibition-opener.yaml +6 -0
- package/lexicons/question-wording-lead.yaml +7 -0
- package/lexicons/rejected-wording.yaml +8 -0
- package/lexicons/request-deadline-section.yaml +11 -0
- package/lexicons/request-prohibition.yaml +8 -0
- package/lexicons/sentence-start-word.yaml +64 -0
- package/lexicons/session-law.yaml +19 -0
- package/lexicons/superlative-goal.yaml +40 -0
- package/lexicons/superlative-part.yaml +22 -0
- package/lexicons/superlative-phrase.yaml +21 -0
- package/lexicons/superlative-purpose.yaml +7 -0
- package/lexicons/superlative-referent.yaml +15 -0
- package/lexicons/superlative-scope.yaml +5 -1
- package/lexicons/telling-cue.yaml +6 -0
- package/lexicons/template-heading.yaml +35 -0
- package/lexicons/text-message-verb.yaml +11 -0
- package/lexicons/uninflected-word.yaml +22 -0
- package/lexicons/unprompted-denial.yaml +113 -0
- package/lexicons/word-suffix.yaml +34 -1
- package/lexicons/wordy-phrase.yaml +2 -2
- package/lexicons/year-reference.yaml +12 -0
- package/package.json +1 -1
- package/src/citation.ts +33 -3
- package/src/index.ts +13 -1
- package/src/initial-stop.ts +80 -0
- package/src/item-style.ts +33 -7
- package/src/law-citation.ts +68 -0
- package/src/lead-initial.ts +28 -0
- package/src/names-read-as-verbs.ts +65 -0
- package/src/pos.ts +33 -1
- package/src/structure.ts +73 -9
package/lexicons/honorific.yaml
CHANGED
|
@@ -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 +1,7 @@
|
|
|
1
|
+
# Words that lead a person's name ("written by J. Smith", "Smith and C.W. Landsea"). After one, initials before a
|
|
2
|
+
# capitalised word that is not a sentence-start-word do not end the sentence. Matched as written.
|
|
3
|
+
id: initial-lead-word
|
|
4
|
+
language: en
|
|
5
|
+
entries:
|
|
6
|
+
- pattern: by
|
|
7
|
+
- pattern: and
|
|
@@ -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 +1,6 @@
|
|
|
1
|
+
# List items that end as the words of a link ("Apply online: click here"). The item points somewhere and is neither a
|
|
2
|
+
# sentence nor a name, even when the link itself was lost in a copy of the page. list-item-form-mix does not judge its form.
|
|
3
|
+
id: link-label-ending
|
|
4
|
+
language: en
|
|
5
|
+
entries:
|
|
6
|
+
- pattern: click here
|
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
# Words that only join the items of a list (defined-name-repeated). In "Registered Mail or Courier Delivery (together, the
|
|
2
|
+
# "Notice Methods")" the bracket names the whole list, not its last item.
|
|
3
|
+
id: list-conjunction
|
|
4
|
+
language: en
|
|
5
|
+
entries:
|
|
6
|
+
- pattern: and
|
|
7
|
+
- pattern: or
|
|
@@ -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 +1,21 @@
|
|
|
1
|
+
# Old written short forms of given names ("Jas. Whittaker", "Wm. Smith", "Joel Wm. Parker"). They stand only before a
|
|
2
|
+
# surname or another name, so their full stop never ends a sentence, even before a name and a comma ("Jas.
|
|
3
|
+
# Whittaker, J. Hocknell"). Forms that are also a whole name (Fred., Alex.) are left out: "I met Fred. Alex came."
|
|
4
|
+
# ends there. Matched as written.
|
|
5
|
+
id: name-abbreviation
|
|
6
|
+
language: en
|
|
7
|
+
entries:
|
|
8
|
+
- pattern: Benj.
|
|
9
|
+
- pattern: Chas.
|
|
10
|
+
- pattern: Danl.
|
|
11
|
+
- pattern: Edw.
|
|
12
|
+
- pattern: Geo.
|
|
13
|
+
- pattern: Jas.
|
|
14
|
+
- pattern: Jno.
|
|
15
|
+
- pattern: Jos.
|
|
16
|
+
- pattern: Nathl.
|
|
17
|
+
- pattern: Richd.
|
|
18
|
+
- pattern: Robt.
|
|
19
|
+
- pattern: Saml.
|
|
20
|
+
- pattern: Thos.
|
|
21
|
+
- pattern: Wm.
|
|
@@ -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 +1,9 @@
|
|
|
1
|
+
# The issue number of a newsletter sent on a schedule (Vol. 12), with … where the number stands. An issue number in the
|
|
2
|
+
# title (a heading before the first sentence) makes the document an issue sent to every subscriber, not a letter
|
|
3
|
+
# to one reader, and it takes no greeting and no closing.
|
|
4
|
+
id: newsletter-issue
|
|
5
|
+
language: en
|
|
6
|
+
entries:
|
|
7
|
+
- pattern: Vol. …
|
|
8
|
+
- pattern: Vol.…
|
|
9
|
+
- pattern: Volume …
|
|
@@ -1,11 +1,13 @@
|
|
|
1
1
|
# Names of the divisions of a document that take a number after them (Part II, Section VIII, Title IV). A Roman
|
|
2
|
-
# numeral right after one of these is the number, not an acronym. Matched as written, or in capitals (PART II).
|
|
2
|
+
# numeral right after one of these is the number, not an acronym. Matched as written, or in capitals (PART II). A US
|
|
3
|
+
# statute cites a Public Law's titles in lower case ("Pub. L. 101–73, title IX, §962").
|
|
3
4
|
id: numbered-division
|
|
4
5
|
language: en
|
|
5
6
|
entries:
|
|
6
7
|
- pattern: Part
|
|
7
8
|
- pattern: Section
|
|
8
9
|
- pattern: Title
|
|
10
|
+
- pattern: title
|
|
9
11
|
- pattern: Chapter
|
|
10
12
|
- pattern: Article
|
|
11
13
|
- pattern: Appendix
|
|
@@ -18,6 +20,7 @@ entries:
|
|
|
18
20
|
- pattern: Division
|
|
19
21
|
- pattern: Subpart
|
|
20
22
|
- pattern: Subtitle
|
|
23
|
+
- pattern: subtitle
|
|
21
24
|
- pattern: Subchapter
|
|
22
25
|
- pattern: Phase
|
|
23
26
|
- pattern: Table
|
|
@@ -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
|
|
@@ -0,0 +1,62 @@
|
|
|
1
|
+
# Sweeping claims about people in general: what most people do, what nobody does. Read by over-general-claim, which
|
|
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).
|
|
11
|
+
id: over-general-claim
|
|
12
|
+
language: en
|
|
13
|
+
entries:
|
|
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
|
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
# A division whose number is left blank in a template (numbering-gap): "Section [●]". The tree does not read it as a
|
|
2
|
+
# division, so the numbering of paragraphs starts again at the line it begins.
|
|
3
|
+
id: placeholder-division
|
|
4
|
+
language: en
|
|
5
|
+
entries:
|
|
6
|
+
- pattern: Section [●]
|
|
7
|
+
- pattern: Article [●]
|
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
# Abbreviations in capitals with full stops that stand before a name as an adjective ("U.S. Census Bureau", "U.K.
|
|
2
|
+
# Parliament"). Before a capitalised word that is not a sentence-start-word, their full stop does not end the sentence.
|
|
3
|
+
# Matched as written.
|
|
4
|
+
id: prepositive-abbreviation
|
|
5
|
+
language: en
|
|
6
|
+
entries:
|
|
7
|
+
- pattern: U.S.
|
|
8
|
+
- pattern: U.K.
|
|
9
|
+
- pattern: U.N.
|
|
10
|
+
- pattern: E.U.
|
|
@@ -0,0 +1,9 @@
|
|
|
1
|
+
# Product names that end in capitals (Adobe Acrobat Reader DC). The capitals are the edition's name inside the product's,
|
|
2
|
+
# not an acronym the writer spells out. Only the whole name is matched, as written: DC alone stays an acronym.
|
|
3
|
+
id: product-name
|
|
4
|
+
language: en
|
|
5
|
+
entries:
|
|
6
|
+
- pattern: Acrobat Reader DC
|
|
7
|
+
- pattern: Acrobat Pro DC
|
|
8
|
+
- pattern: Acrobat Standard DC
|
|
9
|
+
- pattern: Acrobat DC
|
|
@@ -0,0 +1,6 @@
|
|
|
1
|
+
# Words that open a prohibition before a noun (No calls, No food in the lab). list-item-form-mix reads a list item opening
|
|
2
|
+
# with one as neither a verb nor a noun phrase: it is a rule, as "Never feed animals" is. Matched in lower case.
|
|
3
|
+
id: prohibition-opener
|
|
4
|
+
language: en
|
|
5
|
+
entries:
|
|
6
|
+
- pattern: "no"
|
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
# Words right before a quoted term that ask about it ("a definition of what “done” means", "how “ready” is decided").
|
|
2
|
+
# The sentence asks what the term means and defines nothing, so unused-definition does not report the term.
|
|
3
|
+
id: question-wording-lead
|
|
4
|
+
language: en
|
|
5
|
+
entries:
|
|
6
|
+
- pattern: what
|
|
7
|
+
- pattern: how
|
|
@@ -0,0 +1,8 @@
|
|
|
1
|
+
# Words right after a quoted wording that reject it ("high winds" should not be used, …). The wording is not a
|
|
2
|
+
# definition, so unused-definition does not report it. Matched as written.
|
|
3
|
+
id: rejected-wording
|
|
4
|
+
language: en
|
|
5
|
+
entries:
|
|
6
|
+
- pattern: should not be used
|
|
7
|
+
- pattern: is not used
|
|
8
|
+
- pattern: must not be used
|
|
@@ -0,0 +1,11 @@
|
|
|
1
|
+
# A heading, written alone, over the section where a notice states its deadline once for the whole document
|
|
2
|
+
# (a Federal Register notice's "DATES:"). When that section holds a date with a deadline word, every request in the
|
|
3
|
+
# document has that deadline. Compared with the whole heading, its case and a closing colon aside.
|
|
4
|
+
id: request-deadline-section
|
|
5
|
+
language: en
|
|
6
|
+
entries:
|
|
7
|
+
- pattern: dates
|
|
8
|
+
- pattern: key dates
|
|
9
|
+
- pattern: important dates
|
|
10
|
+
- pattern: deadline
|
|
11
|
+
- pattern: deadlines
|
|
@@ -0,0 +1,64 @@
|
|
|
1
|
+
# Function words that start a sentence and are never a surname. After a capital initial and its full stop
|
|
2
|
+
# ("Regulation C. The Guide", "Appendix B. In 2020"), the full stop ends the sentence. Matched as written.
|
|
3
|
+
id: sentence-start-word
|
|
4
|
+
language: en
|
|
5
|
+
entries:
|
|
6
|
+
- pattern: The
|
|
7
|
+
- pattern: This
|
|
8
|
+
- pattern: That
|
|
9
|
+
- pattern: These
|
|
10
|
+
- pattern: Those
|
|
11
|
+
- pattern: A
|
|
12
|
+
- pattern: An
|
|
13
|
+
- pattern: It
|
|
14
|
+
- pattern: Its
|
|
15
|
+
- pattern: In
|
|
16
|
+
- pattern: On
|
|
17
|
+
- pattern: At
|
|
18
|
+
- pattern: For
|
|
19
|
+
- pattern: From
|
|
20
|
+
- pattern: With
|
|
21
|
+
- pattern: By
|
|
22
|
+
- pattern: As
|
|
23
|
+
- pattern: If
|
|
24
|
+
- pattern: When
|
|
25
|
+
- pattern: While
|
|
26
|
+
- pattern: Although
|
|
27
|
+
- pattern: However
|
|
28
|
+
- pattern: Thus
|
|
29
|
+
- pattern: Therefore
|
|
30
|
+
- pattern: We
|
|
31
|
+
- pattern: They
|
|
32
|
+
- pattern: He
|
|
33
|
+
- pattern: She
|
|
34
|
+
- pattern: You
|
|
35
|
+
- pattern: Our
|
|
36
|
+
- pattern: Their
|
|
37
|
+
- pattern: There
|
|
38
|
+
- pattern: Here
|
|
39
|
+
- pattern: Each
|
|
40
|
+
- pattern: Every
|
|
41
|
+
- pattern: All
|
|
42
|
+
- pattern: Some
|
|
43
|
+
- pattern: Many
|
|
44
|
+
- pattern: Most
|
|
45
|
+
- pattern: But
|
|
46
|
+
- pattern: And
|
|
47
|
+
- pattern: So
|
|
48
|
+
- pattern: Yet
|
|
49
|
+
- pattern: Also
|
|
50
|
+
- pattern: Then
|
|
51
|
+
- pattern: After
|
|
52
|
+
- pattern: Before
|
|
53
|
+
- pattern: Under
|
|
54
|
+
- pattern: To
|
|
55
|
+
- pattern: Such
|
|
56
|
+
- pattern: What
|
|
57
|
+
- pattern: Which
|
|
58
|
+
- pattern: How
|
|
59
|
+
- pattern: Why
|
|
60
|
+
- pattern: Additionally
|
|
61
|
+
- pattern: Moreover
|
|
62
|
+
- pattern: Furthermore
|
|
63
|
+
- pattern: Nevertheless
|
|
64
|
+
- pattern: Consequently
|
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
# How a statute's notes cite a law by its own number and sections: "Pub. L. 98–620, title IV, §402(2)", and the page of
|
|
2
|
+
# the volume that prints it, "§2(a), 60 Stat. 237" or "§3.6, Dec. 29, 2009, 75 F.R. 718". A section cited this way is a
|
|
3
|
+
# section of that law, not of this document. position: before is a name written before the law's number (Pub. L.
|
|
4
|
+
# 98–620); position: after is a volume written after the section, between its volume number and page.
|
|
5
|
+
id: session-law
|
|
6
|
+
language: en
|
|
7
|
+
entries:
|
|
8
|
+
- pattern: Pub. L.
|
|
9
|
+
position: before
|
|
10
|
+
- pattern: Public Law
|
|
11
|
+
position: before
|
|
12
|
+
- pattern: Priv. L.
|
|
13
|
+
position: before
|
|
14
|
+
- pattern: Private Law
|
|
15
|
+
position: before
|
|
16
|
+
- pattern: Stat.
|
|
17
|
+
position: after
|
|
18
|
+
- pattern: F.R.
|
|
19
|
+
position: after
|
|
@@ -0,0 +1,40 @@
|
|
|
1
|
+
# Verbs that take a superlative as what is sought or chosen, not as what is claimed: "to achieve the best results",
|
|
2
|
+
# "before deciding the best way", "identify which font was the most legible", "start with the most important tasks". They stand before the superlative, at most
|
|
3
|
+
# a few words away in the same clause. unqualified-superlative does not report a superlative they govern.
|
|
4
|
+
id: superlative-goal
|
|
5
|
+
language: en
|
|
6
|
+
entries:
|
|
7
|
+
- pattern: achieve
|
|
8
|
+
position: before
|
|
9
|
+
- pattern: attain
|
|
10
|
+
position: before
|
|
11
|
+
- pattern: reach
|
|
12
|
+
position: before
|
|
13
|
+
- pattern: come to
|
|
14
|
+
position: before
|
|
15
|
+
- pattern: arrive at
|
|
16
|
+
position: before
|
|
17
|
+
- pattern: aim for
|
|
18
|
+
position: before
|
|
19
|
+
- pattern: strive for
|
|
20
|
+
position: before
|
|
21
|
+
- pattern: decide
|
|
22
|
+
position: before
|
|
23
|
+
- pattern: determine
|
|
24
|
+
position: before
|
|
25
|
+
- pattern: choose
|
|
26
|
+
position: before
|
|
27
|
+
- pattern: select
|
|
28
|
+
position: before
|
|
29
|
+
- pattern: pick
|
|
30
|
+
position: before
|
|
31
|
+
- pattern: identify
|
|
32
|
+
position: before
|
|
33
|
+
- pattern: start with
|
|
34
|
+
position: before
|
|
35
|
+
- pattern: begin with
|
|
36
|
+
position: before
|
|
37
|
+
- pattern: prioritize
|
|
38
|
+
position: before
|
|
39
|
+
- pattern: prioritise
|
|
40
|
+
position: before
|
|
@@ -0,0 +1,22 @@
|
|
|
1
|
+
# Nouns that name a part of something the text describes. A superlative whose noun is one of them ranks the parts of that
|
|
2
|
+
# whole ("the most important part of the formula", "the customer is the most important role" in a workshop), not the
|
|
3
|
+
# world: the set is the whole's parts. English only: the noun follows the superlative's modifiers.
|
|
4
|
+
id: superlative-part
|
|
5
|
+
language: en
|
|
6
|
+
entries:
|
|
7
|
+
- pattern: part
|
|
8
|
+
- pattern: parts
|
|
9
|
+
- pattern: role
|
|
10
|
+
- pattern: roles
|
|
11
|
+
- pattern: step
|
|
12
|
+
- pattern: steps
|
|
13
|
+
- pattern: aspect
|
|
14
|
+
- pattern: aspects
|
|
15
|
+
- pattern: element
|
|
16
|
+
- pattern: elements
|
|
17
|
+
- pattern: component
|
|
18
|
+
- pattern: components
|
|
19
|
+
- pattern: stage
|
|
20
|
+
- pattern: stages
|
|
21
|
+
- pattern: phase
|
|
22
|
+
- pattern: phases
|
|
@@ -0,0 +1,21 @@
|
|
|
1
|
+
# Set phrases that hold a superlative but claim nothing is the best. A superlative inside one is not reported by
|
|
2
|
+
# unqualified-superlative. "Even the best" concedes ("even the best teams slip"); "the best case" is a hypothetical.
|
|
3
|
+
# "Make the most of" and "do the most good" are idioms of effort; "the most recent" places in time; "the most common"
|
|
4
|
+
# reports how often something occurs; "the most important thing" orders the writer's own points.
|
|
5
|
+
id: superlative-phrase
|
|
6
|
+
language: en
|
|
7
|
+
entries:
|
|
8
|
+
- pattern: even the best
|
|
9
|
+
- pattern: even the most
|
|
10
|
+
- pattern: even on the best
|
|
11
|
+
- pattern: even in the best
|
|
12
|
+
- pattern: even for the best
|
|
13
|
+
- pattern: even with the best
|
|
14
|
+
- pattern: the best case
|
|
15
|
+
- pattern: the best-case
|
|
16
|
+
- pattern: make the most of
|
|
17
|
+
- pattern: get the most out of
|
|
18
|
+
- pattern: do the most good
|
|
19
|
+
- pattern: the most recent
|
|
20
|
+
- pattern: the most common
|
|
21
|
+
- pattern: the most important thing
|
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
# Words after a superlative's noun that name its set only when a gerund follows: "the most important tool for creating
|
|
2
|
+
# the culture" (tools for creating it), "the most prominent intervention for combating misinformation". "For" with a
|
|
3
|
+
# noun ("the best opportunity for government") names who gains, not a set.
|
|
4
|
+
id: superlative-purpose
|
|
5
|
+
language: en
|
|
6
|
+
entries:
|
|
7
|
+
- pattern: for
|
|
@@ -0,0 +1,15 @@
|
|
|
1
|
+
# Words that point at one member of a set, after a superlative subject and its verb: "The best plan is the one you will
|
|
2
|
+
# keep", "The most important divergence is the second". The sentence says which one is the most, not that something is.
|
|
3
|
+
id: superlative-referent
|
|
4
|
+
language: en
|
|
5
|
+
entries:
|
|
6
|
+
- pattern: one
|
|
7
|
+
- pattern: ones
|
|
8
|
+
- pattern: first
|
|
9
|
+
- pattern: second
|
|
10
|
+
- pattern: third
|
|
11
|
+
- pattern: last
|
|
12
|
+
- pattern: former
|
|
13
|
+
- pattern: latter
|
|
14
|
+
- pattern: whichever
|
|
15
|
+
- pattern: whatever
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Words that say what a superlative is the most of. position is the side of the superlative they stand on.
|
|
2
2
|
# English puts them after the superlative's noun phrase, with a noun phrase after them: "the best pizza in Chicago",
|
|
3
|
-
# "the most famous of the sculptures".
|
|
3
|
+
# "the most famous of the sculptures", "the best thing about this gathering", "the best models at the frontier".
|
|
4
4
|
id: superlative-scope
|
|
5
5
|
language: en
|
|
6
6
|
entries:
|
|
@@ -8,3 +8,7 @@ entries:
|
|
|
8
8
|
position: after
|
|
9
9
|
- pattern: of
|
|
10
10
|
position: after
|
|
11
|
+
- pattern: about
|
|
12
|
+
position: after
|
|
13
|
+
- pattern: at
|
|
14
|
+
position: after
|
|
@@ -0,0 +1,6 @@
|
|
|
1
|
+
# Words that name who said a quotation, or when (in Japanese, 申し込んだら、「…」と言われています). The English phrases weasel-word
|
|
2
|
+
# reads ("many experts say", "studies show") do not report a quotation, so there are none; the list exists so both languages
|
|
3
|
+
# name the same lists.
|
|
4
|
+
id: telling-cue
|
|
5
|
+
language: en
|
|
6
|
+
entries: []
|
|
@@ -0,0 +1,35 @@
|
|
|
1
|
+
# The sections of a textbook proposal or report outline. A heading counts for its group when it starts with the pattern
|
|
2
|
+
# (case ignored). One or two are ordinary in a real proposal; ai-structure counts the outline when four groups appear.
|
|
3
|
+
id: template-heading
|
|
4
|
+
language: en
|
|
5
|
+
entries:
|
|
6
|
+
- { pattern: executive summary, group: summary }
|
|
7
|
+
- { pattern: summary, group: summary }
|
|
8
|
+
- { pattern: overview, group: summary }
|
|
9
|
+
- { pattern: background, group: background }
|
|
10
|
+
- { pattern: current situation, group: background }
|
|
11
|
+
- { pattern: current state, group: background }
|
|
12
|
+
- { pattern: problem statement, group: background }
|
|
13
|
+
- { pattern: the problem, group: background }
|
|
14
|
+
- { pattern: proposed solution, group: proposal }
|
|
15
|
+
- { pattern: proposal, group: proposal }
|
|
16
|
+
- { pattern: our proposal, group: proposal }
|
|
17
|
+
- { pattern: recommendation, group: proposal }
|
|
18
|
+
- { pattern: recommendations, group: proposal }
|
|
19
|
+
- { pattern: expected benefits, group: benefits }
|
|
20
|
+
- { pattern: benefits, group: benefits }
|
|
21
|
+
- { pattern: expected outcomes, group: benefits }
|
|
22
|
+
- { pattern: expected impact, group: benefits }
|
|
23
|
+
- { pattern: costs, group: costs }
|
|
24
|
+
- { pattern: cost, group: costs }
|
|
25
|
+
- { pattern: budget, group: costs }
|
|
26
|
+
- { pattern: implementation, group: implementation }
|
|
27
|
+
- { pattern: implementation plan, group: implementation }
|
|
28
|
+
- { pattern: timeline, group: implementation }
|
|
29
|
+
- { pattern: rollout, group: implementation }
|
|
30
|
+
- { pattern: risks, group: risks }
|
|
31
|
+
- { pattern: risk, group: risks }
|
|
32
|
+
- { pattern: risks and mitigation, group: risks }
|
|
33
|
+
- { pattern: next steps, group: next }
|
|
34
|
+
- { pattern: conclusion, group: next }
|
|
35
|
+
- { pattern: conclusions, group: next }
|