expected_changes.toml

# Every rule needs `issue`; optional `name_regex` and `fields` narrow
# it. An unexplained diff is a release blocker until classified (spec
# S5). Rules are seeded from docs/superpowers/plans/notes-m12-diffs.md
# and the `classification="fix(...)"` rows in tests/v2/cases.py; keep
# each entry's `name_regex`/`fields` as tight as the diff allows.
# File order is not load-bearing: compare.py sorts `name_regex` rules
# ahead of `fields`-only ones before matching.

[[change]]
issue = "fix(#271/#272) native-script CJK: family-first order, hangul segmentation, the kana license and the nakaguro"
# '毛 泽东', '김민준': script_orders flips first/last for a name written
# wholly in Han or Hangul, and the Korean surnames that now ship as
# default vocabulary additionally split an unspaced hangul token into
# last + first. '高橋 みなみ', 'マイケル・ジャクソン': #272 extends the
# same order table to kana-bearing Japanese names and makes the
# katakana middle dot a token separator, which moves pieces between the
# same three fields. Seeded from the fix(#271) and fix(#272) rows in
# tests/v2/cases.py.
#
# One rule, not two, because it is one diff shape: both issues move
# name pieces between first/middle/last on native-script CJK input, and
# splitting the class by issue would need a rule per script with no
# gain in tightness (the fields list is already the narrow half).
#
# Scoped by script, which is exactly the scope of the behavior --
# nothing here can touch a name with no CJK character in it. Han's
# astral block (U+20000-U+323AF) is deliberately left out of the class:
# no name in either corpus reaches it, and a rule should be no wider
# than the diffs it has to explain. Extend it -- and the sync pin in
# tests/v2/test_regex_sync.py, which fails if the two disagree -- if
# one ever does. The kana spans are BMP-only for a different reason:
# supplementary-plane kana is hentaigana and other archaic forms no
# modern name uses, so _SCRIPT_RANGES does not list it either.
#
# U+FF65 is the one span here that _SCRIPT_RANGES does NOT have, and
# it is deliberate: the halfwidth middle dot separates tokens like its
# fullwidth twin, so 'ﾏｲｹﾙ･ｼﾞｬｸｿﾝ' splits where 1.4 left one token,
# but halfwidth kana is excluded from CLASSIFICATION on purpose (a
# separate normalization problem). The rest of the halfwidth block
# (U+FF66-U+FF9F) is left out for the usual tightness reason, and it
# was measured rather than assumed: a dotless halfwidth name such as
# 'ﾏｲｹﾙ ｼﾞｬｸｿﾝ' is byte-identical on both sides, so covering the
# block would pre-excuse a future regression on a shape that is
# parity today. The dot is the whole mechanism; the dot is the whole
# span.
#
# corpus_cjk.jsonl (#295) exists so this rule fires in every real
# run: build_cjk_corpus.py harvests every CJK-bearing text in
# tests/v2/cases.py -- the fix(#271)/fix(#272)/fix(shime-mark) rows
# AND the parity rows, whose value here is pinning NON-diffs (マイケル
# must not change against 1.4) -- closing the blind spot the other
# two corpora have by construction: v1's banks had no reason to test
# CJK, and build_issues_corpus.py requires an internal space, which
# unspaced names never have.
name_regex = "[\\u3005-\\u3006\\u3040-\\u309F\\u30A0-\\u30FF\\u3400-\\u4DBF\\u4E00-\\u9FFF\\uF900-\\uFAFF\\uAC00-\\uD7A3\\uFF65-\\uFF65]"
fields = ["first", "middle", "last"]

[[change]]
issue = "fix(#274) maiden markers consumed"
name_regex = "(?i)\\b(n[ée]e|born|geb\\.?|roz\\.?)\\b"
fields = ["maiden", "middle", "last"]

[[change]]
issue = "fix(comma-family) lone post-comma piece routes to suffix/title, not first"
# 'Smith, Dr.' / 'Andrews, M.D.': v1 put the lone strict-suffix-or-title
# post-comma piece in `first`; 2.0 routes it to `suffix`/`title` instead
# (family/`last` is unchanged either way -- "pre-comma is definitionally
# family").
name_regex = ","
fields = ["first", "title", "suffix"]

[[change]]
issue = "fix(suffix-routing) two-token name with unambiguous trailing suffix stays suffix"
# 'Johnson PhD' / 'Mr. Johnson PhD': v1 routed a lone trailing suffix
# to family/first (no comma present); 2.0 keeps recognized suffixes in
# `suffix`.
fields = ["first", "last", "suffix"]

[[change]]
issue = "fix(suffix-delimiter-rendering) no-space delimiter core token kept whole"
# Only fires when a custom suffix delimiter is configured (Policy /
# Constants.suffix_delimiters); the corpus runs with default policy, so
# this rule is expected to match nothing here. Kept for documentation
# parity with tests/v2/cases.py's 'suffix_delimiter_no_space_core' row
# (anti-#100, migration plan deviation 5).
name_regex = "/"
fields = ["suffix"]

[[change]]
issue = "ambiguous-surname-acronym data change: parenthesized (MA)/(DO) now stays nickname"
# suffix_acronyms_ambiguous gained 'ma'/'do' so bare 'Jack Ma' keeps its
# surname (v1 parity restored); side effect: parenthesized/quoted "MA"
# or "DO" no longer escape to suffix (v1 did, since v1 treated them as
# unambiguous there) -- they now fall through to nickname parsing.
# Not expected to fire against this corpus (no such strings survived
# into the v1 banks); kept for documentation completeness.
name_regex = "(?i)[(\"'](m\\.?a\\.?|d\\.?o\\.?)[)\"']"
fields = ["suffix", "nickname"]

[[change]]
issue = "feat(#269) Arabic بن prefix chains onto family (non-Latin new-recognition)"
# '‏محمد بن سلمان‏': #269 adds the native-script Arabic
# patronymic particle بن ("bin"/"son of") to PREFIXES/
# NON_FIRST_NAME_PREFIXES. v1 had no such entry, so it left بن a plain
# middle-name token ('سلمان' alone as last); 2.0 now chains it onto the
# family the same way 'von'/'bin' (Latin) do, giving family 'بن سلمان'.
# This is new-recognition on non-Latin input -- the exact behavior
# #269 exists to add -- not a Latin-corpus regression, so it is
# classified rather than reverted.
# Word-bounded: a bare "بن" would also match the substring inside e.g.
# لبنان ("Lebanon") and silently absorb unrelated middle/last diffs.
name_regex = "\\bبن\\b"
fields = ["middle", "last"]

[[change]]
issue = "feat(#273) typographic nickname delimiters recognized by default"
# 'John “Jack” Kennedy', 'Hans „Hansi“ Müller', 'Jean «Petit» Dupont':
# v1 knew only straight quotes and parentheses, so a smart-quoted or
# guillemet-wrapped nickname leaked into `middle` as literal text.
# Matches only when such a delimiter is actually present -- the ASCII
# pairs stay unclassified, since a diff there would be a regression.
name_regex = "[“”„«»「」『』（）]"
fields = ["middle", "nickname"]

[[change]]
issue = "fix(cjk-delimited-nickname) delimiter recognition compounds with the CJK order flip"
# '山田「タロ」太郎', '山田 太郎 (マイケル・ジャクソン)': one name, two
# intended changes at once -- the corner-bracket/nakaguro handling
# (2.0's typographic delimiters; 2.1's dot separator rendering the
# nickname join with a space) changes `nickname`, while the same
# name's wholly-CJK remainder takes the 2.1 family-first flip in
# first/last. Neither single-change rule may claim the union (the
# delimiter rule's fields exclude first/last, the CJK rule's exclude
# nickname -- each on purpose, so a lone regression in the other's
# fields stays loud). Both lookaheads are required: the delimiters
# alone would match 'John 「Jack」 Kennedy' -- the brackets sit in CJK
# Symbols and Punctuation, OUTSIDE every classified span, so a Latin
# name can carry them -- and would then absorb a bare first/last
# regression on it. Requiring a classified codepoint too confines the
# rule to names the order flip can actually reach. The second
# lookahead's class is the same hand copy of _SCRIPT_RANGES the rule
# above carries, pinned by the same sync test. One absorption is
# inherent and accepted: a nickname-ONLY diff on a nakaguro name
# ('マイケル・ジャクソン') classifies here, because subset-matching
# cannot REQUIRE a field to have changed. Positional note: this rule
# overlaps the CJK rule above and the delimiter rule below; within
# the name_regex tier file order decides which label a diff reports
# under, so it sits after the tighter single-change rules on purpose.
# The issue slug deliberately avoids the literal #271/#272 strings --
# test_regex_sync's differential pin selects the canonical CJK rule
# by those substrings and asserts it is unique.
name_regex = "(?s)(?=.*[「」『』・･])(?=.*[\\u3005-\\u3006\\u3040-\\u309F\\u30A0-\\u30FF\\u3400-\\u4DBF\\u4E00-\\u9FFF\\uF900-\\uFAFF\\uAC00-\\uD7A3\\uFF65-\\uFF65])"
fields = ["first", "last", "nickname"]

[[change]]
issue = "feat(#269) non-Latin titles/conjunctions recognized"
# 'г-н Иван Петров' (Cyrillic title), 'Хосе И Мария Сантос' (Cyrillic
# conjunction И joining two given names). v1 shipped Latin-only
# vocabulary, so these were plain name tokens and everything shifted
# one position. New recognition on non-Latin input -- the point of
# #269 -- not a Latin-corpus regression.
#
# Cyrillic only, and only the three fields the shift can touch. The
# first draft allowed five fields across four scripts, which put every
# Arabic name in the corpus -- including ones that are currently
# PARITY -- into its shadow, and pre-excused Greek and Hebrew, against
# which nothing has ever been compared. A leading title or an absorbed
# conjunction moves a word from `first` to `title`, or from `middle`
# into `first`; it cannot reach `last` or `suffix`. Widen this only
# with a name that demonstrates the need, and prefer a new rule per
# script over loosening this one -- the \bبن\b rule below is the
# model.
name_regex = "[\\u0400-\\u04FF]"
fields = ["title", "first", "middle"]

[[change]]
issue = "fix(leading-credential) a split 'Ph. D.' before the name stays one unit"
# 'Ph. D. John Smith'. v1 healed the adjacent 'Ph.'/'D.' pair only when
# it TRAILED; leading, it split them -- title 'Ph.', given 'D.', and
# the real given name pushed to middle. 2.0 keeps the credential whole
# and routes it to `suffix`, which is the post-nominal field, so a
# leading credential lands there rather than in `title`. Slightly odd
# positionally, and still strictly better than manufacturing a given
# name out of 'D.'.
#
# Anchored to the START on purpose. Trailing 'Ph. D.' is PARITY and
# stays unclassified below; widening this regex would mask a
# regression in the shape that is the whole reason fix_phd exists.
name_regex = "^Ph\\. ?D\\."
fields = ["title", "first", "middle", "suffix"]

# Deliberately NOT a [[change]] rule: TRAILING 'Ph. D.' split-token
# healing ('John Ph. D.', 'John Smith, Ph. D.') is PARITY, not a 2.0
# behavior change -- v1's fix_phd healing of the adjacent 'Ph.'/'D.'
# pair into one suffix unit is replicated exactly by 2.0's 'joined'
# vocab tag (tests/v2/cases.py classification="parity" on both
# 'phd_split' and 'suffix_comma_split_phd'; verified empirically, zero
# diff against the 1.4 worker). Adding a suppression rule for it would
# risk masking a real regression in this exact shape, so it is
# intentionally left unclassified: if it ever starts diffing, the
# harness must fail. (The leading case above is a separate shape, which
# is why it needed its own anchored rule rather than a widened one.)