547 lines
28 KiB
Go
547 lines
28 KiB
Go
package pipeline
|
||
|
||
import (
|
||
"fmt"
|
||
"regexp"
|
||
"sort"
|
||
"strings"
|
||
"unicode"
|
||
)
|
||
|
||
// sanitizer.go: the output-sanitizer (D30.3) — a deterministic verdict-axis gate on the
|
||
// FINAL chunk text that catches the "instant unreadability" defect classes NO existing
|
||
// gate detects (exp12 root-cause + flagman §5). It is OPT-IN (Gates.Sanitizer.Enabled),
|
||
// following the coverage gate's discipline: when enabled a defect flips the chunk to
|
||
// flagged (D2 flag+skip — the contaminated output never commits to TM/export), else it is
|
||
// a no-op. Pure and deterministic (no time/rand, sorted detail) so a resume re-derives the
|
||
// identical verdict — its rule version folds into the snapshot only when enabled
|
||
// (sanitizerVersion, mirroring coverageSnapshot), and moves to verdictSnapshotID once
|
||
// content-addressed resume lands (D15.2).
|
||
//
|
||
// Six classes, each tuned PRECISION over recall (fire only on a high-confidence signal;
|
||
// the ambiguous middle stays silent — a false flag turns a good chunk into an export
|
||
// placeholder, worse than a missed defect for an opt-in readability gate):
|
||
//
|
||
// 1. leading service preamble — «Вот отредактированный перевод: …» (gemini 6/6, exp12 §4.1)
|
||
// 2. trailing note/edit block — appended «Примечание:/Внесённые правки:/Что изменено:» meta
|
||
// 3. markdown ### header — «### Глава 1» (8/54 finals of stage A — D29 finding)
|
||
// 4. Latin-script insertion — an untranslated Latin phrase/heavy Latin in the ru output
|
||
// 5. broken word form — homoglyph-mixed token or an invalid Cyrillic sign bigram
|
||
// 6. CJK-leak in the final — a stray Han ideograph / kana / fullwidth glyph in the ru output
|
||
// («…охотники,却有 деньги!» arms/C/17.0 — D38.1; below the ≥15%
|
||
// echo threshold classify() already catches, so a sparse leak)
|
||
//
|
||
// DISPOSITION-BY-CLASS (D38 infra-pack): the classes split into two tiers so a chunk is not
|
||
// silently lost to an export placeholder when the leak is a REMOVABLE cosmetic span (D35.4a —
|
||
// ch5/ch20 chapter openers dropped whole for a leading «### Глава N»):
|
||
// - COSMETIC (strippable, exported + flagged for a human, cosmeticOnly()==true): the markdown
|
||
// header (3) and the CJK-leak (6). The leak sits in a bounded span stripCosmetic() removes
|
||
// deterministically, leaving readable prose; the chunk is flagged sanitizer_stripped (a
|
||
// "auto-cleaned, verify" signal), NOT dropped.
|
||
// - SUBSTANTIVE (dropped to a placeholder, current behaviour): the preamble (1), trailing
|
||
// note (2), Latin insertion (4) and broken word (5). Their contamination has no reliable
|
||
// removable boundary (a preamble may swallow real narration; a Latin clause / broken token is
|
||
// lost content), so the output is not trusted — flagged sanitizer_defect + skipped.
|
||
//
|
||
// HONEST recall gap (documented, precision over recall): the broken-word class catches only
|
||
// the two ZERO-false-positive signatures (invalid Cyrillic sign bigrams, mixed Cyrillic/Latin
|
||
// token). The junction-duplication split heuristic («Первопред предок») was REMOVED (D33.1б): it
|
||
// false-flagged ordinary prose sharing a morphemic boundary. A word broken WITHOUT an invalid
|
||
// character («Первок предок» split into two individually-valid tokens) or a grammatical-but-wrong
|
||
// form («валуне») is NOT offline-detectable without a morphology/dictionary pass (Ф2) — left silent.
|
||
|
||
// sanitizerVersion versions the rules below (folded into the snapshot when the gate is
|
||
// enabled, like cheapGateVersion/coverageGateVersion): editing any pattern shifts the
|
||
// resolved disposition of flagged chunks, so a bump is a loud --resnapshot. [D15.2 note:
|
||
// this is a VERDICT version — once content-addressed resume lands it moves to
|
||
// verdictSnapshotID and a rule edit re-classifies free instead of re-paying the book.]
|
||
// v2 (D33.1/33.2): tail edit-summary «Основные правки для справки:» now flags; the
|
||
// junction-duplication split detector was removed (false-flagged prose); markdown/heavy-Latin
|
||
// narrowed. A verdict-axis change → loud --resnapshot + golden re-capture (invariant №8).
|
||
// v3 (D38 infra-pack): added the CJK-leak class (Han/kana/fullwidth in the ru final) and the
|
||
// cosmetic-vs-substantive disposition split (the markdown header and CJK-leak are now STRIPPED
|
||
// and exported flagged, not dropped to an empty placeholder — D35.4a). Both shift the resolved
|
||
// disposition/export of a flagged chunk → a loud --resnapshot + golden re-capture (invariant №8).
|
||
// v4 (D38 infra-pack, adversarial review): stripCosmetic now FOLDS content-bearing fullwidth ASCII
|
||
// («１２３»→«123», not deleted) and ideographic comma/period, space-replaces dropped ideographs (no
|
||
// word-merge), removes an emptied bracket pair, and no longer reformats a legit «2 : 1» — all shift
|
||
// a stripped chunk's EXPORT text → a loud --resnapshot + golden re-capture (invariant №8).
|
||
const sanitizerVersion = "sanitizer-v4"
|
||
|
||
// sanitizer tuning constants (versioned by sanitizerVersion).
|
||
const (
|
||
// trailingRegionLines: a note/edit header counts only when it sits in the LAST N
|
||
// non-empty lines (a meta block the model appended), so a legitimate mid-narrative
|
||
// «Примечание» in dialogue does not fire.
|
||
trailingRegionLines = 6
|
||
// latinPhraseWords: a run of this many SPACE-adjacent Latin word-tokens is a leaked
|
||
// untranslated phrase/sentence (a couple of proper names never reaches it). Set to 5
|
||
// (адверсариальное ревью): a ≤4-word quoted foreign motto («sic transit gloria mundi»)
|
||
// is legit source-preserved content and must NOT be dropped. ⚠ ACCEPTED recall/precision
|
||
// edge: a deliberately-quoted foreign phrase of ≥5 words («to be or not to be») still
|
||
// trips it — rare, and the gate is opt-in (a redrive surfaces it to a human).
|
||
latinPhraseWords = 5
|
||
// latinHeavyShare / latinHeavyTokens: heavy Latin contamination — Latin letters are a
|
||
// large share of all letters AND there are several Latin tokens (both required, so a
|
||
// short chunk with one long Latin brand name does not trip the share alone).
|
||
latinHeavyShare = 0.25
|
||
latinHeavyTokens = 5
|
||
)
|
||
|
||
// sanitizerResult is the per-chunk outcome: a count per class plus deterministic detail.
|
||
type sanitizerResult struct {
|
||
Preamble int `json:"preamble,omitempty"`
|
||
TrailingNote int `json:"trailing_note,omitempty"`
|
||
MarkdownHeader int `json:"markdown_header,omitempty"`
|
||
LatinInsert int `json:"latin_insert,omitempty"`
|
||
BrokenWord int `json:"broken_word,omitempty"`
|
||
CJKLeak int `json:"cjk_leak,omitempty"`
|
||
Detail []string `json:"detail,omitempty"`
|
||
}
|
||
|
||
func (s sanitizerResult) total() int {
|
||
return s.Preamble + s.TrailingNote + s.MarkdownHeader + s.LatinInsert + s.BrokenWord + s.CJKLeak
|
||
}
|
||
|
||
// cosmeticOnly reports whether the ONLY classes that fired are the STRIPPABLE cosmetic ones
|
||
// (markdown header and/or CJK-leak) — the strip-and-export tier (D35.4a). A single substantive
|
||
// class (preamble/trailing-note/latin/broken-word) pulls the whole chunk into the skip tier: its
|
||
// contamination has no reliable removable boundary, so the output is not trusted even if a
|
||
// cosmetic leak also happens to be present. False when nothing fired.
|
||
func (s sanitizerResult) cosmeticOnly() bool {
|
||
return s.total() > 0 && s.Preamble == 0 && s.TrailingNote == 0 && s.LatinInsert == 0 && s.BrokenWord == 0
|
||
}
|
||
|
||
// summary is the human-readable disposition detail for a sanitizer flag (deterministic —
|
||
// Detail is sorted in sanitizeOutput). Kept short (the first two findings) for the log/row.
|
||
func (s sanitizerResult) summary() string {
|
||
if len(s.Detail) == 0 {
|
||
return "output-sanitizer defect"
|
||
}
|
||
if len(s.Detail) > 2 {
|
||
return strings.Join(s.Detail[:2], "; ") + fmt.Sprintf("; …(+%d)", len(s.Detail)-2)
|
||
}
|
||
return strings.Join(s.Detail, "; ")
|
||
}
|
||
|
||
// sanitizeOutput runs all six classes over one chunk's FINAL translated text.
|
||
func sanitizeOutput(text string) sanitizerResult {
|
||
var r sanitizerResult
|
||
if det := detectLeadingPreamble(text); det != "" {
|
||
r.Preamble++
|
||
r.Detail = append(r.Detail, det)
|
||
}
|
||
if det := detectTrailingNote(text); det != "" {
|
||
r.TrailingNote++
|
||
r.Detail = append(r.Detail, det)
|
||
}
|
||
if n, det := detectMarkdownHeaders(text); n > 0 {
|
||
r.MarkdownHeader = n
|
||
r.Detail = append(r.Detail, det...)
|
||
}
|
||
if det := detectLatinInsertion(text); det != "" {
|
||
r.LatinInsert++
|
||
r.Detail = append(r.Detail, det)
|
||
}
|
||
if n, det := detectBrokenWords(text); n > 0 {
|
||
r.BrokenWord = n
|
||
r.Detail = append(r.Detail, det...)
|
||
}
|
||
if n, det := detectCJKLeak(text); n > 0 {
|
||
r.CJKLeak = n
|
||
r.Detail = append(r.Detail, det...)
|
||
}
|
||
sort.Strings(r.Detail)
|
||
return r
|
||
}
|
||
|
||
// --- 1. leading service preamble ------------------------------------------------
|
||
|
||
// leadingPreamblePatterns match a service preamble at the very START of the output — the
|
||
// «Вот отредактированный перевод: …» leak (gemini 6/6, exp12 §4.1). PRECISION over recall
|
||
// (адверсариальное ревью: a lax rule dropped clean chapter openings like «Вот такой вариант
|
||
// развития — самый вероятный.», «Вот его вариант: он молча ушёл.»). Two guards make it tight:
|
||
// 1. terminator is a COLON only — the em-dash «—» is ubiquitous in narration, so it is NOT
|
||
// a terminator (a service preamble is a labeled prefix ending in «:»);
|
||
// 2. the phrase must be a genuine TRANSLATION/EDIT service label, not merely «lead + common
|
||
// noun»: either an edit-adjective (отредактированн/исправленн/улучшенн) + a перевод/текст/
|
||
// вариант noun, or «перевод фрагмента/текста/…», or «ниже приведён … перевод/текст».
|
||
//
|
||
// Go RE2 \w/\b are ASCII-only, so Cyrillic uses [а-яё].
|
||
var leadingPreamblePatterns = []*regexp.Regexp{
|
||
// «Вот/Представляю/Привожу … отредактированный/исправленный перевод/текст/вариант …:»
|
||
// (the edit-adjective front-gate holds precision, so the tail-to-colon may be long — the
|
||
// gemini leak carries «… с соблюдением всех терминов из глоссария:»).
|
||
regexp.MustCompile(`(?is)^\s*(?:вот|представляю|привожу|держите)\s+[^\n:]{0,40}?(?:отредактированн|исправленн|улучшенн)[а-яё]+\s+(?:перевод|текст|вариант)[а-яё]*[^\n:]{0,120}?:`),
|
||
// «Отредактированный/Исправленный перевод/текст/вариант …:» (label at the very start)
|
||
regexp.MustCompile(`(?is)^\s*(?:отредактированн|исправленн|улучшенн)[а-яё]+\s+(?:перевод|текст|вариант)[а-яё]*[^\n:]{0,120}?:`),
|
||
// «(Вот) перевод фрагмента/текста/отрывка/главы/черновика:»
|
||
regexp.MustCompile(`(?is)^\s*(?:вот\s+)?перевод\s+(?:фрагмента|текста|отрывка|главы|черновика)\s*:`),
|
||
// «Ниже приведён/представлен … перевод/отредактированный текст:»
|
||
regexp.MustCompile(`(?is)^\s*ниже\s+(?:привед[её]н|представлен|дан|след)[а-яё]*\s+[^\n:]{0,40}?(?:перевод|отредактированн|текст)[а-яё]*[^\n:]{0,20}?:`),
|
||
}
|
||
|
||
func detectLeadingPreamble(text string) string {
|
||
t := strings.TrimSpace(text)
|
||
for _, re := range leadingPreamblePatterns {
|
||
if loc := re.FindStringIndex(t); loc != nil {
|
||
return "ведущая служебная преамбула: " + preview(strings.TrimSpace(t[:loc[1]]))
|
||
}
|
||
}
|
||
return ""
|
||
}
|
||
|
||
// --- 2. trailing note / edit block ----------------------------------------------
|
||
|
||
// trailingNoteRE matches a note/edit meta-HEADER at line start: «Примечание:», «Заметки
|
||
// переводчика», «Комментарий:», «(прим. перев.)». PRECISION over recall (адверсариальное
|
||
// ревью: «Комментатор захлёбывался…», «Заметка белела на столе.», «Пояснения не требовалось.»,
|
||
// «Сноска объясняла обычай.» are ordinary narrative nouns/gerunds — NOT headers). So the header
|
||
// word MUST be followed by a COLON, or be «примечание/заметки/комментарий + переводчика/редактора»,
|
||
// or be the «(прим. перев./ред.)» marker. Only counted inside the trailing region (below).
|
||
var trailingNoteRE = regexp.MustCompile(`(?i)^[*_>\s-]{0,4}(?:(?:примечани[ея]|заметк[аи]|комментари[йяю]|пояснени[ея]|сноск[аи])\s*:|(?:примечани[ея]|заметк[аи]|комментари[йяю])\s+(?:переводчик|редактор)[а-яё]*|прим\.\s*(?:перев|ред)\.?)`)
|
||
|
||
// editMetaAnywhereRE matches UNAMBIGUOUS editor meta-commentary that is a defect wherever it
|
||
// appears (not only trailing): «Внесённые правки:», «Что изменено:», «Список правок:», and the
|
||
// gemini tail leak «Основные правки для справки: …» (D33.1а — the A5/5_1 defect the gate exists
|
||
// to catch, exp12:229: the leading-preamble rule caught the head form «Вот отредактированный
|
||
// перевод:» but NOT this trailing edit-summary). The generic «Изменения:/Правки:» alone were
|
||
// REMOVED (адверсариальное ревью — «Изменения — вот что пугало его.» / «Правка — дело тонкое.»
|
||
// are common narrative openers), keeping only editor-specific compounds that never occur in prose.
|
||
// «основн…правк» is gated to «… для справки» OR a colon so a bare narrative «Основные правки внёс
|
||
// редактор» (no summary label) does not fire.
|
||
var editMetaAnywhereRE = regexp.MustCompile(`(?im)^[*_>\s-]{0,4}(?:(?:внесённ|внесен)[а-яё]+\s+правк|основн[а-яё]+\s+правк[а-яё]*(?:\s+для\s+справк[а-яё]+|\s*:)|что\s+(?:было\s+)?(?:изменен|исправлен)|список\s+(?:правок|изменений)|список\s+внесённых)`)
|
||
|
||
func detectTrailingNote(text string) string {
|
||
if loc := editMetaAnywhereRE.FindStringIndex(text); loc != nil {
|
||
return "утёкший блок правок редактора: " + preview(strings.TrimSpace(firstLineAt(text, loc[0])))
|
||
}
|
||
lines := nonEmptyLines(text)
|
||
start := len(lines) - trailingRegionLines
|
||
if start < 0 {
|
||
start = 0
|
||
}
|
||
for _, ln := range lines[start:] {
|
||
if trailingNoteRE.MatchString(ln) {
|
||
return "хвостовой блок заметок/примечаний: " + preview(strings.TrimSpace(ln))
|
||
}
|
||
}
|
||
return ""
|
||
}
|
||
|
||
// --- 3. markdown ### header -----------------------------------------------------
|
||
|
||
// markdownHeaderRE matches a markdown ATX header line («### Глава», «# Title»): 1–6 hashes,
|
||
// a space, then a LETTER or DIGIT. «#1» / «№5» / a lone «#» do not match (no space+text); and
|
||
// (D33.2) a decorative scene-break rendered with hashes — «# # #», «## ***», «### ---» — no
|
||
// longer matches, since the char after the hashes is punctuation, not a header word/number.
|
||
var markdownHeaderRE = regexp.MustCompile(`(?m)^\s{0,3}#{1,6}\s+[\p{L}\p{Nd}]`)
|
||
|
||
func detectMarkdownHeaders(text string) (int, []string) {
|
||
var det []string
|
||
n := 0
|
||
for _, ln := range strings.Split(text, "\n") {
|
||
if markdownHeaderRE.MatchString(ln) {
|
||
n++
|
||
det = append(det, "markdown-заголовок в выходе: "+preview(strings.TrimSpace(ln)))
|
||
}
|
||
}
|
||
return n, det
|
||
}
|
||
|
||
// --- 4. Latin-script insertion --------------------------------------------------
|
||
|
||
// detectLatinInsertion flags an untranslated Latin PHRASE (≥ latinPhraseWords Latin words
|
||
// separated only by SINGLE SPACES — a real «the quick brown fox», not an alphanumeric id) OR
|
||
// heavy Latin contamination (Latin ≥ latinHeavyShare of all letters AND ≥ latinHeavyTokens
|
||
// Latin tokens). Requiring space-adjacency is load-bearing: a hex/id run like «138fd5c384e3»
|
||
// or «a1b2c3d4» yields several single-letter Latin tokens with NO space between them, which
|
||
// must NOT read as a Latin phrase (a false positive the golden fixture's tags exposed). A
|
||
// handful of Latin proper names stays silent.
|
||
func detectLatinInsertion(text string) string {
|
||
toks := scriptTokens(text)
|
||
maxRun, run, heavyLatTokens := 0, 0, 0
|
||
for _, tk := range toks {
|
||
switch {
|
||
case tk.lat:
|
||
if tk.adjacent && run > 0 {
|
||
run++ // a Latin word separated from the previous Latin word by one space
|
||
} else {
|
||
run = 1 // phrase start (digit/punct separator or a non-Latin predecessor)
|
||
}
|
||
// Heavy-Latin count EXCLUDES capitalized/brand tokens (D33.2): «iPhone», «iPad»,
|
||
// «MacBook», «Google» are legit proper nouns, so a list of 5+ brands must not trip the
|
||
// heavy-share gate. A genuinely leaked English clause is lowercase past its first word,
|
||
// so it still clears latinHeavyTokens (and a real multi-word Latin PHRASE is caught by
|
||
// maxRun below, which still counts every Latin token).
|
||
if !hasUpperLatin(tk.text) {
|
||
heavyLatTokens++
|
||
}
|
||
if run > maxRun {
|
||
maxRun = run
|
||
}
|
||
case tk.cyr || tk.mixed:
|
||
run = 0
|
||
}
|
||
}
|
||
if maxRun >= latinPhraseWords {
|
||
return "латинская вставка (фраза из подряд идущих латинских слов)"
|
||
}
|
||
latinLetters, cyrLetters := 0, 0
|
||
for _, ru := range text {
|
||
if unicode.Is(unicode.Latin, ru) {
|
||
latinLetters++
|
||
} else if unicode.Is(unicode.Cyrillic, ru) {
|
||
cyrLetters++
|
||
}
|
||
}
|
||
total := latinLetters + cyrLetters
|
||
if total > 0 && heavyLatTokens >= latinHeavyTokens && float64(latinLetters)/float64(total) >= latinHeavyShare {
|
||
return "латиница-врезки: тяжёлая доля латиницы в ru-выходе"
|
||
}
|
||
return ""
|
||
}
|
||
|
||
// hasUpperLatin reports whether s contains an uppercase Latin letter — the brand/proper-noun
|
||
// signature («iPhone», «MacBook», «Google») excluded from the heavy-Latin token count (D33.2).
|
||
func hasUpperLatin(s string) bool {
|
||
for _, ru := range s {
|
||
if unicode.Is(unicode.Latin, ru) && unicode.IsUpper(ru) {
|
||
return true
|
||
}
|
||
}
|
||
return false
|
||
}
|
||
|
||
// --- 5. broken word forms -------------------------------------------------------
|
||
|
||
// invalidSignRE matches Cyrillic sign bigrams that never occur in valid Russian: a hard/soft
|
||
// sign at a word START that is FOLLOWED BY A LETTER (a broken token like «ьзал»), or two signs
|
||
// adjacent (ъь/ьъ/ьь/ъъ). Requiring the following letter excludes a STANDALONE «ъ»/«ь» — a
|
||
// metalinguistic mention of the letter itself, «Буква ъ называлась ером.» (адверсариальное
|
||
// ревью nit). High precision otherwise: word-initial-sign-then-letter and doubled signs are
|
||
// impossible in well-formed text. \P{L} (non-letter), not RE2's ASCII-only \b.
|
||
var invalidSignRE = regexp.MustCompile(`(?i)(?:^|\P{L})[ъь][а-яё]|[ъь][ъь]`)
|
||
|
||
func detectBrokenWords(text string) (int, []string) {
|
||
var det []string
|
||
seen := map[string]bool{}
|
||
add := func(s string) {
|
||
if !seen[s] {
|
||
seen[s] = true
|
||
det = append(det, s)
|
||
}
|
||
}
|
||
// (a) invalid Cyrillic sign bigrams.
|
||
if invalidSignRE.MatchString(text) {
|
||
add("невалидная кириллическая биграмма (мягкий/твёрдый знак в начале слова или подряд)")
|
||
}
|
||
// (b) mixed Cyrillic+Latin within one letter-run token (homoglyph artifact).
|
||
// NOTE: the junction-duplication split detector («Первопред предок») was REMOVED (D33.1б).
|
||
// It fired identically on ordinary prose whose adjacent tokens merely share a ≥4-rune
|
||
// morphemic boundary («около колонны/колодца», «стало талой» — «около» is a frequent
|
||
// preposition → flag-storm on 25 legit chapters), while its only synthetic target had an
|
||
// overlap fraction (4/9) INDISTINGUISHABLE from those false positives (4/5): no threshold on
|
||
// overlap length or share separates them, and the canonical «Первок предок» was never caught
|
||
// anyway (recall gap — TestSanitizerBrokenWordRecallGap). Deterministic split-duplication with
|
||
// no invalid sign / homoglyph needs a morphology pass (Ф2), so it stays silent here.
|
||
for _, tk := range scriptTokens(text) {
|
||
if tk.mixed {
|
||
add("смешение кириллицы и латиницы в одном слове (гомоглиф): " + preview(tk.text))
|
||
}
|
||
}
|
||
return len(det), det
|
||
}
|
||
|
||
// --- 6. CJK-leak in the final --------------------------------------------------
|
||
|
||
// isCJKLeakRune reports whether r is a stray CJK glyph that has NO place in a Russian final: a
|
||
// Han ideograph, kana, a fullwidth/halfwidth form (U+FF00–FFEF — «，（）！» etc.), or a CJK
|
||
// symbol/punctuation (U+3001–303F — «、。「」»). The ideographic SPACE U+3000 is deliberately
|
||
// EXCLUDED (it is an indent artifact, not a content leak — research/18 §C#4 "draft-21 includes a
|
||
// U+3000 indent → 9 real leaks"): stripCosmetic normalises it to a plain space, but it does not
|
||
// alone FIRE the class, so a legitimately-indented chunk is not flag-stormed. In clean Russian
|
||
// prose every one of these is count-0, so the class is high precision. The intrinsic classify()
|
||
// already flags a ≥15%-CJK output as an ECHO (cjk_artifact, substantive) BEFORE the sanitizer
|
||
// runs, so this class only ever sees a SPARSE leak in otherwise-Russian text.
|
||
func isCJKLeakRune(r rune) bool {
|
||
switch {
|
||
case unicode.Is(unicode.Han, r):
|
||
return true
|
||
case unicode.Is(unicode.Hiragana, r) || unicode.Is(unicode.Katakana, r):
|
||
return true
|
||
case r >= 0xFF00 && r <= 0xFFEF: // fullwidth & halfwidth forms
|
||
return true
|
||
case r >= 0x3001 && r <= 0x303F: // CJK symbols & punctuation, EXCLUDING U+3000 (ideographic space)
|
||
return true
|
||
}
|
||
return false
|
||
}
|
||
|
||
// detectCJKLeak counts maximal runs of leak runes in the final text and returns a deduped detail
|
||
// per distinct run. A single run («却有») is enough to fire — the class is COSMETIC, so the whole
|
||
// chunk is not lost: stripCosmetic removes the run and the remainder exports (flagged for review).
|
||
func detectCJKLeak(text string) (int, []string) {
|
||
var det []string
|
||
seen := map[string]bool{}
|
||
n := 0
|
||
rs := []rune(text)
|
||
for i := 0; i < len(rs); {
|
||
if !isCJKLeakRune(rs[i]) {
|
||
i++
|
||
continue
|
||
}
|
||
j := i
|
||
for j < len(rs) && isCJKLeakRune(rs[j]) {
|
||
j++
|
||
}
|
||
n++
|
||
run := string(rs[i:j])
|
||
if !seen[run] {
|
||
seen[run] = true
|
||
det = append(det, "CJK-утечка в ru-выходе: "+preview(run))
|
||
}
|
||
i = j
|
||
}
|
||
return n, det
|
||
}
|
||
|
||
// --- deterministic strip of the COSMETIC classes (D35.4a export fix) -------------
|
||
|
||
// leadingMarkdownStripRE matches the leading markdown ATX prefix on a line (optional indent, 1–6
|
||
// hashes, blank(s)) directly before a header WORD/number — the same shape markdownHeaderRE fires
|
||
// on. It captures the first header rune so ReplaceAll keeps the heading text, dropping only the
|
||
// «### » artifact («### Глава 5» → «Глава 5»). A decorative «### ---» scene break (punctuation
|
||
// after the hashes) does NOT match, so it is left intact (and it never fired the class either).
|
||
var leadingMarkdownStripRE = regexp.MustCompile(`(?m)^[ \t]{0,3}#{1,6}[ \t]+([\p{L}\p{Nd}])`)
|
||
|
||
// stripCosmetic deterministically removes the two STRIPPABLE cosmetic leak classes — leading
|
||
// markdown headers and CJK-leak runs — and tidies the whitespace the removal leaves, so the
|
||
// remainder is readable. It is a PURE function (resume re-derives the identical export), invoked
|
||
// ONLY on output the sanitizer classified as cosmeticOnly (classifyOutput guarantees the result
|
||
// is non-empty and clean — sanitizeOutput(stripCosmetic(x)).total()==0 — before tagging it
|
||
// sanitizer_stripped). It never crosses newlines when tidying, so paragraph structure is kept.
|
||
func stripCosmetic(text string) string {
|
||
// 1) markdown header prefixes → keep the heading text, drop the «#### » artifact.
|
||
out := leadingMarkdownStripRE.ReplaceAllString(text, "$1")
|
||
// 2) neutralise CJK-leak runes. CONTENT-BEARING glyphs are FOLDED, not dropped (adversarial
|
||
// review MAJOR): a fullwidth ASCII form is a wrong-glyph rendering of a plain char, so «１２３»
|
||
// folds to «123» (the number is kept, not deleted) and «，」→«,» — the same NFKC fold the
|
||
// memory normaliser uses. Only genuinely contentless runes (Han/kana/CJK brackets/symbols) are
|
||
// removed, and a removed run leaves a SINGLE SPACE so adjacent Russian words do not merge
|
||
// («нашёл特产древний» → «нашёл древний», not «нашёлдревний»). U+3000 → a plain space (indent).
|
||
var b strings.Builder
|
||
b.Grow(len(out))
|
||
for _, r := range out {
|
||
switch {
|
||
case r == ' ': // U+3000 ideographic space → plain space
|
||
b.WriteByte(' ')
|
||
case r >= 0xFF01 && r <= 0xFF5E: // fullwidth ASCII form → fold to plain ASCII (１→1, Ａ→A, ，→,)
|
||
b.WriteRune(r - 0xFEE0)
|
||
case r == '、': // ideographic comma → plain comma (keep the clause boundary)
|
||
b.WriteByte(',')
|
||
case r == '。': // ideographic full stop → plain period
|
||
b.WriteByte('.')
|
||
case isCJKLeakRune(r): // Han / kana / CJK brackets / other symbol → drop, leaving a space
|
||
b.WriteByte(' ')
|
||
default:
|
||
b.WriteRune(r)
|
||
}
|
||
}
|
||
out = b.String()
|
||
// 3) tidy the seams the removal created, per line (horizontal whitespace only — never a
|
||
// newline): collapse doubled spaces, drop a bracket/quote pair the strip emptied («(羅漢拳)» →
|
||
// «()» → removed), drop a space now sitting before closing punctuation or after an opening
|
||
// bracket/quote (never-correct Russian spacing), and trim trailing blanks. ':' is deliberately
|
||
// NOT in the closing-punct set: a space-before-colon is legitimate in a Russian ratio/score/time
|
||
// («счёт 2 : 1») and must not be reformatted (adversarial review — false positive).
|
||
out = multiSpaceRE.ReplaceAllString(out, " ")
|
||
out = emptyBracketRE.ReplaceAllString(out, "")
|
||
out = spaceBeforePunctRE.ReplaceAllString(out, "$1")
|
||
out = spaceAfterOpenRE.ReplaceAllString(out, "$1")
|
||
out = multiSpaceRE.ReplaceAllString(out, " ") // an emptied bracket may leave a doubled space
|
||
out = trailingHSpaceRE.ReplaceAllString(out, "")
|
||
return out
|
||
}
|
||
|
||
var (
|
||
multiSpaceRE = regexp.MustCompile(`[ \t]{2,}`)
|
||
emptyBracketRE = regexp.MustCompile(`\([ \t]*\)|«[ \t]*»|\[[ \t]*\]`)
|
||
spaceBeforePunctRE = regexp.MustCompile(`[ \t]+([,.!?;…»)\]])`)
|
||
spaceAfterOpenRE = regexp.MustCompile(`([«(\[])[ \t]+`)
|
||
trailingHSpaceRE = regexp.MustCompile(`(?m)[ \t]+$`)
|
||
)
|
||
|
||
type scriptToken struct {
|
||
text string
|
||
cyr bool // Cyrillic-only
|
||
lat bool // Latin-only
|
||
mixed bool // both scripts in one letter run (homoglyph artifact)
|
||
adjacent bool // separated from the previous token by exactly a single space (junction check)
|
||
}
|
||
|
||
// scriptTokens splits text into maximal letter-run tokens (letters only; digits/hyphens/
|
||
// spaces/punctuation are separators), tagging Cyrillic-only / Latin-only / mixed-script and
|
||
// whether the token is separated from the previous token by exactly a single space
|
||
// (adjacency — a duplication artifact sits inside a phrase, not across punctuation/newline).
|
||
func scriptTokens(text string) []scriptToken {
|
||
var out []scriptToken
|
||
var b strings.Builder
|
||
hasLat, hasCyr := false, false
|
||
gap := "" // separator run since the previous token: "" none yet, " " one space, "x" other
|
||
flush := func() {
|
||
if b.Len() > 0 {
|
||
out = append(out, scriptToken{
|
||
text: b.String(),
|
||
cyr: hasCyr && !hasLat,
|
||
lat: hasLat && !hasCyr,
|
||
mixed: hasLat && hasCyr,
|
||
adjacent: gap == " ",
|
||
})
|
||
b.Reset()
|
||
gap = ""
|
||
}
|
||
hasLat, hasCyr = false, false
|
||
}
|
||
for _, ru := range text {
|
||
switch {
|
||
case unicode.Is(unicode.Latin, ru):
|
||
b.WriteRune(ru)
|
||
hasLat = true
|
||
case unicode.Is(unicode.Cyrillic, ru):
|
||
b.WriteRune(ru)
|
||
hasCyr = true
|
||
default:
|
||
flush()
|
||
if ru == ' ' && gap == "" {
|
||
gap = " "
|
||
} else {
|
||
gap = "x" // newline / punctuation / tab / a second space breaks adjacency
|
||
}
|
||
}
|
||
}
|
||
flush()
|
||
return out
|
||
}
|
||
|
||
// --- shared helpers -------------------------------------------------------------
|
||
|
||
func nonEmptyLines(text string) []string {
|
||
var out []string
|
||
for _, ln := range strings.Split(text, "\n") {
|
||
if strings.TrimSpace(ln) != "" {
|
||
out = append(out, ln)
|
||
}
|
||
}
|
||
return out
|
||
}
|
||
|
||
// firstLineAt returns the line containing byte offset off.
|
||
func firstLineAt(text string, off int) string {
|
||
start := strings.LastIndexByte(text[:off], '\n') + 1
|
||
end := strings.IndexByte(text[off:], '\n')
|
||
if end < 0 {
|
||
return text[start:]
|
||
}
|
||
return text[start : off+end]
|
||
}
|