Skip to content

OCR fix lists: adopt the safest community rules from #12644 #12649

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
niksedk wants to merge 1 commit into from
Closed

OCR fix lists: adopt the safest community rules from #12644 #12649

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions Dictionaries/eng_OCRFixReplaceList.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3395,6 +3395,12 @@
<RegEx find="(2 )(nd\b)" replaceWith="2$2" />
<RegEx find="(3 )(rd\b)" replaceWith="3$2" />
<RegEx find="([456789])( th\b)" replaceWith="$1th" />
<!-- ü misread as ii: Fiihrer/Obergruppenfiihrer etc. (from #12644) -->
<RegEx find="iihrer" replaceWith="ührer" />
<!-- ñ misread as fi: Sefior/sefiorita, compafiero (from #12644) -->
<RegEx find="\b([Ss])efior" replaceWith="${1}eñor" />
<RegEx find="ompafier" replaceWith="ompañer" />
<RegEx find="ompafiar" replaceWith="ompañar" />
</RegularExpressions>
<RegularExpressionsIfSpelledCorrectly>
<RegEx find="\[([A-Zl]+)\]" replaceAllFrom="l" replaceAllTo="I" spellCheck="$1" replaceWith="[$1]" />
Expand Down
23 changes: 22 additions & 1 deletion Dictionaries/fra_OCRFixReplaceList.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -267,7 +267,23 @@
</PartialLines>
<BeginLines />
<EndLines />
<RegularExpressions />
<RegularExpressions>
<!-- From #12644 (community-contributed, safety-reviewed) -->
<!-- "Il y a" misread as "ILy a" -->
<RegEx find="\bILy a\b" replaceWith="Il y a" />
<!-- d'ou is always d'où -->
<RegEx find="\b([Dd])'([Oo])u\b" replaceWith="${1}'${2}ù" />
<!-- S misread as 5 in S'il -->
<RegEx find="5 *'il\b" replaceWith="S'il" />
<!-- spaced apostrophe: s 'il / s 'ils -->
<RegEx find="([Ss]) 'il(s?)\b" replaceWith="${1}'il${2}" />
<!-- l misread as I in l'a -->
<RegEx find="\bI'a\b" replaceWith="l'a" />
<!-- spaced apostrophe after t' before vowel/h: "Je t' aime" -->
<RegEx find=" t' ([aehiouyéèêàùâîôûAEHIOUYÉÈÊÀÙÂÎÔÛ])" replaceWith=" t'${1}" />
<!-- S misread as 5 in SOS (letter O only - never the number 505) -->
<RegEx find="\b5(\.*)O(\.*)5(\.*)\b" replaceWith="S${1}O${2}S${3}" />
</RegularExpressions>
<RegularExpressionsIfSpelledCorrectly>

<!-- ============================================================ -->
Expand Down Expand Up @@ -372,5 +388,10 @@
<!-- inLondon → in London -->
<RegEx find="\bin([A-Z][a-zæøåöäéèàùâêîôûëïœç]+)\b" spellCheck="$1" replaceWith="in $1" />


<!-- From #12644: è/à misread - only applied when the fixed word is in the dictionary -->
<RegEx find="\b([MmPp])[eéêë]re\b" spellCheck="${1}ère" replaceWith="${1}ère" />
<RegEx find="\b([Tt])r[eéêë]s\b" spellCheck="${1}rès" replaceWith="${1}rès" />
<RegEx find="\bL[äáâ]\b" spellCheck="Là" replaceWith="Là" />
</RegularExpressionsIfSpelledCorrectly>
</OCRFixReplaceList>
4 changes: 4 additions & 0 deletions Dictionaries/nld_OCRFixReplaceList.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,6 +108,8 @@
<Word from="ziin" to="zijn" />
<Word from="zonderjou" to="zonder jou" />
<Word from="Zonderjou" to="Zonder jou" />
<!-- from #12644 -->
<Word from="wanner" to="wanneer" />
</WholeWords>
<PartialWordsAlways />
<PartialWords>
Expand Down Expand Up @@ -137,6 +139,8 @@
<RegEx find="\beIk" replaceWith="elk" />
<RegEx find="\bler(land|se|s|)\b" replaceWith="Ier$1" />
<RegEx find="comite\b" replaceWith="comité" />
<!-- doubled apostrophe before 'n / 't (from #12644) -->
<RegEx find="''([nt])\b" replaceWith="'${1}" />
</RegularExpressions>
<RegularExpressionsIfSpelledCorrectly>

Expand Down
5 changes: 5 additions & 0 deletions Dictionaries/spa_OCRFixReplaceList.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -366,6 +366,9 @@
<Word from="Bartomeu" to="Bertomeu" />
<Word from="Iocalizarlo" to="localizarlo" />
<Word from="Ilámame" to="llámame" />
<!-- ! misread as l (from #12644) -->
<Word from="niñal" to="niña!" />
<Word from="túl" to="tú!" />
</WholeWords>
<PartialWordsAlways />
<PartialWords />
Expand Down Expand Up @@ -948,5 +951,7 @@
<RegEx find="\Bi(log[ao]s?\b)" replaceWith="í$1" />
<RegEx find="\bIes\b" replaceWith="les" />
<RegEx find="\bIos\b" replaceWith="los" />
<!-- ü misread as ii: Fiihrer/Obergruppenfiihrer etc. (from #12644) -->
<RegEx find="iihrer" replaceWith="ührer" />
</RegularExpressions>
</OCRFixReplaceList>