====== Replacment rules ====== ===== Global ===== ==== First run ==== /\xad/u -> "" /\xa0/u -> " " /–/ -> "-" /ʼ/ -> "'" /č/ -> "č" /&/ -> "&" /\(\d+\)\.$/ -> "." /\.\(\d+\)$/ -> "." /^\s*\(\d+\) / -> "" /\((\w+)$/ -> "(\1)" /<[.]{3}|…>/ -> "" /[.]{3}|…/ -> "" /\(\)/ -> "" /\($/ -> "" /^<$/ -> "" /(\d+º)/ -> "\1" /(http:\/\/[a-z.-]+)"?\s*(\.| \w)/ -> "\1\2" /\((A\d-\d{4}\/(?:\d{2})?\d{2})\)/ -> "\1" /(?)(A\d-\d{4}(?:\/(?:\d{2})?\d{2})?)/ -> "\1" /\[(\d{4}\/\d{4}\([A-Z]+\))\]/ -> "\1" /\(((?:[A-Z]+\(\d+\))?[A-Z\d\/ ]*\d{4} - C\d-\d{4})[7\/]((?:\d{2})?\d{2}(?: - \d{4}\/\d{4}\/?(?:\([A-Z]+\))?)?)\)/ -> "\1/\2" / ,/ -> ',' /(\([^)]+)$/ -> '\1)' /\s\s+/ -> ' ' ==== Second run ==== /" ?([^"”]+)["”]/u -> "\1" /« ?([^»]+?) ?»/u -> "\1" /(?<=>) ([:;.!?])/ -> "\1" /<\/quote> ,/ -> "," /^"\s+/ -> "" /^\)\s+/ -> "" /&/ -> "&" /,,+/ -> "," ===== Local (language specific) ===== ==== First run ==== === Danish === /[»]([^«]+)«/u -> "\1" === German === /„([^“]+)(["”“])([^„]+„[^\2]+\2)*/u -> "\1" /(?:,,)([\w ]+)"/u -> "\1" === English === /\' ?s\b/u -> "’s" /["]([^\']+)\'/u -> "\1" === Spanish === / -(?=\w)/u -> " —" /(?<=\w)-(\W)/u -> "—\1" === Greek === /\' \b/u -> "’ " === Finish === /\b(\p{Lu}+): ?n\b/u -> "\1:n" === French === /\b(l|d|n|j|t|m|qu|c|s|jusqu|lorsqu|aujourd|puisqu|quelqu|quoiqu)\' ?/iu -> "\1" /»([^»]+?)»/u -> "\1" === Italian === /\be[\'’]/u -> "è" /\bE[\'’]/u -> "È" /\bpò\b/u -> "po’" /\bpo\'\b/u -> "po’" /\bperchè\b/u -> "perché" /\bpoichè\b/u -> "poiché" /\baffinchè\b/u -> "affinché" /\bpero\b/u -> "però" /\b(un|l|d|dell|nell|all|dall|sull)\' ?/iu -> "\1’" /[“"]([^”]+)”/u -> "\1" /["]([^»]+)»/u -> "\1" /»([^»]+?)»/u -> "\1" === Portuguese === /["]([^»]+)»/u -> "\1" === Swedish === /\b(\p{Lu}+): ?s\b/u -> "\1:s" ==== Second run ==== === Bulgarian === // -> "" === Czech === // -> "" === Danish === // -> "" === German === // -> "" /<\/quote>(\w)/ -> "-\1" === Greek === // -> "" === English === // -> "" === Spanish === // -> "" === Estonian === // -> "" === Finnish === // -> "" === French === /(? " \1" // -> "" === Hungarian === // -> "" === Italian === // -> "" === Lithuanian === // -> "" === Latvian === // -> "" === Dutch === // -> "" === Polish === // -> "" === Portuguese === // -> "" === Romanian === // -> "" === Slovak === // -> "" === Slovenian === // -> "" === Swedish === // -> ""