org.languagetool.resource.segment.srx Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of languagetool-core Show documentation
Show all versions of languagetool-core Show documentation
LanguageTool is an Open Source proofreading software for English, French, German, Polish, Romanian, and more than 20 other languages. It finds many errors that a simple spell checker cannot detect like mixing up there/their and it detects some grammar problems.
ON! is een omroep.
\bκ\.λπ\.\s
\bπ\.χ\.\s
\b(Ιαν|Φεβ|Μα[ϊρ]|Απρ|Ιου[νλ]|Αυγ|Σεπ|Οκτ|Νοε|Δεκ)\.\s
[\.!;…][\u00BB\u2019\u201D\u203A"'\p{Pe}\u0002]*\s
[\.!;…]['"\u00BB\u2019\u201D\u203A\p{Pe}\u0002]*
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!;…]\s
\p{Lu}\p{Ll}
\b[Aa]dw?\.\s
\bafr\.\s
\bakad\.\s
\b[Aa]l\.\s
\bam\.\s
\bamer\.\s
\barch\.\s
\b[Aa]rt\.\s
\bartyst\.\s
\bastr\.\s
\baustr\.\s
\bbałt\.\s
\bbdb\.\s
\bbł\.\s
\bbm\.\s
\bbr\.\p{Pe}?\s
[^\p{Lu}]
\bbry[gt]\.\s
\bcentr\.\s
\bces\.\s
\bchem\.\s
\bchiń\.\s
\bchir\.\s
\bc\.k\.\s
\bc\.o\.\s
\bcyg\.\s
\bcyw\.\s
\bcyt\.\s
\bczes\.\s
\bczw?\.\s
\b[Cc]d\.\s
\bczyt\.\s
\bćw\.\s
\bćwicz\.\s
\bdaw\.\s
\bdcn\.\s
\bdekl\.\s
\bdemokr\.\s
\bdet\.\s
\bdiec\.\s
\bdł\.\s
\bdn\.\s
\bdo[tlp]\.\s
[^\p{Lu}]
\bdost\.\s
\bdosł\.\s
\bh\.c\.\s
\bds\.\s
\bdst\.\s
\bduszp\.\s
\bdypl\.\s
\begz\.\s
\bekol\.\s
\bekon\.\s
\belektr\.\s
\bem\.\s
\bew\.\s
\bfab\.\s
\bfarm\.\s
\bfot\.\s
\bfr\.\s
\bgat\.\s
\bgastr\.\s
\bgeogr\.\s
\bgeol\.\s
\bgimn\.\s
\bgłęb\.\s
\bgm\.\s
\bgodz\.\s
\bgórn\.\s
\bgosp\.\s
\bgr\.\s
\bgram\.\s
\bhist\.\s
\bhiszp\.\s
\b[Hh]r\.\s
\bhot\.\s
\bid\.\s
\bin\.\s
\bim\.\s
\biron\.\s
\bjn\.\s
\bkard\.\s
\bkat\.\s
\bkatol\.\s
\bk\.k\.\s
\bkk\.\s
\bko?l\.\s
\bk\.p\.a\.\s
\bkpc\.\s
\bk\.p\.c\.\s
\bkpt\.\s
\bkr\.\s
\bk\.r\.\s
\bkrak\.\s
\bk\.r\.o\.\s
\bkryt\.\s
\bkult\.\s
\blaic\.\s
\błac\.\s
\bniem\.\s
\bwoj\.\s
\b[Nn][bp]\.\s
\bpo[lw]\.\s
\bm\.in\.\s
\b[Pp][ts]\.\s
\bcdn\.\s
\bjw\.\s
\b[Rr]y[cs]\.\s
\btj\.\s
\b[Tt]zw\.\s
\btzn\.\s
\b[Zz]ob\.\s
\bsłow\.\s
[^s]\.pl\.\s
\p{Lu}\p{Ll}+
\bp[wnl]\.\s
\bang\.\s
\bu[lb]\.\s?
\bal\.\s
\bk\.\s
\bn\.\s
\b[Oo]k\.\s
[\p{Ll}\d]
\b[\d,\.]*ty[sś]\.\p{Pe}?\s
[\p{Ll}\d]+
\b[Nn]r\.\s
\d
\bw[wł]\.\s
\bur\.\s
\bzm\.\s
\bżyd\.\s
\bżarg\.\s
\bżyw\.\s
\bwy[łdm]\.\s
\b[bu]p\.\s
\bwyst\.\s
\b(?iu)mazeł\stow\.\s
\b[Tt]ow\.\s
\bo\.\s
\b([sS]p|st|[Ss]półdz|społ|spółgł|[Ss]to[łw])\.\s
\bzn\.\s
\bzew\.\s
\bzewn\.\s
\bzdr\.\s
\bzazw\.\s
\bzast\.\s
\bzaw\.\s
\bzał\.\s
\bzal\.\s
\bzam\.\s
\bzak\.\s
\bzakł\.\s
\bzagr\.\s
\bzach\.\s
\b[Aa]dw\.\s
\b[Ll]ek\.\s
\bmed\.\s
\b[Mm]ec\.\s
\b[Dd]oc\.\s
\b[Dd]y[wr]\.\s
\b[Ii]nż\.\s
\b(?iu)mgr\.\s
\b[dD][hr]\.\s
\b[pP]\.\s
\p{Lu}\p{Ll}+
\b[Rr]ed\.\)?\s
\b(?iu)pro[fk]\.\s
\bhab\.\s
\b[Pp]łk\.\s
\b([Nn]a|[Pp]o)dkom\.\s
\b[kK]s\.\s
\b(?iu)gen\.\s
\b(?iu)por\.\s
\b[Rr]eż\.\s
\b[Pp]rzyp\.\s
\bp\.n\.e\.\s
\bdyr\.\smuz\.\s
\b[śŚ][pwW]\.\s
\bw\.\s
((?:X{0,2})(?:V?I{0,3}|I[VX]))(?<=[XVI]+)
\bII?\społ\.\s
[IVX]+
\betc\.\s
\p{Ll}
\bit[dp]\.\s
[„”"]?\p{Ll}
\bproc\.\)?\s
\p{Ll}|\p{Lu}\p{Lu}+
\b[rwn]\.\s
\p{Ll}
\bit[dp]\.\s
\p{Ll}
\bcdn\.\s
\p{Ll}
\b[Ss]zer\.\s
\bjw\.\s
\p{Ll}
\bn\.e\.\s
\p{Ll}
\bw\.\s
\p{Ll}
\bn[tn]\.\s
\p{Ll}
\b[dm]l\.\s
\p{Ll}
\bdag\.\s
\p{Ll}
\b[cd]?m\.\s
\p{Ll}
\b[Zz][Łł]\.\s
\p{Ll}
\b[Gg][rR]\.\s
\p{Ll}
\b[d]?kg\.\s
\p{Ll}
\bml[nd]\.\s
\p{Ll}
\bnpl\.\s
\p{Ll}
\bpkt\.\s
[\p{Ll}\d]
\bstr\.\s
[\p{Ll}\d]
\b[Tt]ab\.\s
[\p{Ll}\d]
\btel\.\s
\b[ptw]g\.\s
\p{Ll}
\bcos\.\s
\p{Ll}
\bcosec\.\s
\p{Ll}
\bsec\.\s
\p{Ll}
\bsin\.\s
\p{Ll}
\brkm\.\s
\p{Ll}
\bust\.\s
\d
\bpar\.\s
\d
\blit\.\s
\p{Ll}\p{Pe}?\p{P}?\s
\b[Pp]on\.\s
\p{Ll}
\b[Ss]ob\.\s
\p{Ll}
\bba!\s
\p{Ll}
\bpo[zk]\.\s
\bop\.\s
cit\.
\b[Oo][Oo]\.\s
\b([CDSR]z|Ch)\.\s
\p{Ll}
\b[rls]\.\s
[1-9]+
[\d-–]+\sl\.\s
\p{Ll}
\((?:od|do|w)\s[1-9]\d*\sr\.\s
\d+\sr\.\s
[^\p{Lu}]
\bn\.e\.\s
[^\p{Lu}]
\bt\.\s
\d+
\b[,uoi]\ss\.\s
\b[Nn]ajśw\.\s
\b[Nn]a\sos\.\s
\barab\.\s
[^\x00-\x80]+
\bT\.
Love\b
\bpl\.
Open[oO]ffice
\bha\.\s
[\p{Ll}]
\bmin\.\s
[\p{Ll}\d]
\bW\s\d{4}\sr\.\s
[\p{Lu}-–—„"]
\b\d+\.\s
\p{Ll}|\p{Lu}{2,}
\b\p{L}\.\s
\p{L}\.\s
\b\p{L}\.
\p{L}\.
\.\p{L}+\.\s
\p{Ll}
[\s\(\[][\p{L}&&[^rwn]]\.\s+
\p{Ll}\p{Ll}|\p{Lu}[\p{Punct}\p{Lu}]
['"„][\.!?…]['"”]\s
["”']\s*
\s*\p{Ll}
[!?]+\p{Pe}
\p{Ll}
[\p{Ps}][!?]+[\p{Pe}]
[\[\(]*\.\.\.[\]\)]*
\p{Ll}
[\[\(]*…[\]\)]*
\p{Ll}
\b\p{Lu}\.\s\p{Lu}\.\s
\b\p{Lu}\.\p{Lu}\.\s
\b\p{Lu}\p{Ll}\.\s?
\p{Lu}[^\p{Lu}]
\.\p{Lu}\p{Ll}\.\s?
\p{Lu}[^\p{Lu}]
\s(?<!\.)[„"\p{Ps}]?[A-Z]\.\s
\p{Ll}|\p{Lu}\p{Ll}\p{Ll}+
^[„"]?[A-ZŚĆŻŹ]\.\s
\p{Ll}|\p{Lu}\p{Ll}\p{Ll}+
\(\p{Lu}?\p{Ll}+\.\s
\s[A-Z]\.\s
\(\d
\bDz\.\s?U\.\s
[\p{Ll}&&[^aeouiyęąó]][\p{Ll}&&[^aeouiyęąó]]+\.\s
\p{Ll}+
[\.!?…]+['"\p{Pe}\u00BB\u2019\u201D\u203A\u0002]*\s
[\p{Ps}-–—]\s?\p{Ll}
[\.!?…]['"\u00BB\u2019\u201D\u203A\u0002]*\p{Pe}\s
\p{Ll}
p\.\s
n\.\s?e\.
[\.!?…]['"\p{Pe}\u00BB\u2019\u201D\u203A\u0002¹²³]*\s
[\.!?…]['»"”\p{Pe}]*
\p{Lu}[^\p{Lu}\.]
\s\p{L}[\.!?…]\s
\p{Lu}\p{Ll}
:
[—\-–] \p{Lu}
[\u00A0\s]
\n
[a-zA-Z][!\?][\s\u00A0]
\)[\s\u00A0][a-zA-Z]
Yahoo![\s\u00A0]
\p{Ll}
[A-Z]\.[A-Z]\.
[A-Z]\b
\bA\.
I\b
\bS\.
I\b
\bL\.
A\b
\bU\.
[SK]\b
\bI\.
S\b
\bM\.
Z\b
\b(https?|ftp|file|chrome|chromium|android|(chrome|moz)\-extension):///?[A-Za-z0-9\-]+\.
[A-Za-z0-9\-]+(\.|\b)
\b[A-Za-z0-9\-]+\.
[A-Za-z0-9\-]+\.(com|net|org|info|de|es|edu|co|eu|nl|io|cn|uk|gov|biz|ca|tk|ru|br|jp|pl|be|dev|co|fr|dk|se)(\.|\b)
\b[nN]o\.[\s\u00A0]
\p{N}
\bP[Hh]\.[\s\u00A0]?
D\.?
\b([Aa]vg|[Ee]d|pp|[Vv]iz|i\.?[\s\u00A0]*e|[Vvol]|[Rr]col|maj|Lt|[Ff]ig|[Ff]igs|[Vv]iz|[Vv]ols|[Aa]pprox|[Aa]cq|[Ii]ncl?|[Ee]xcl|[Aa]cc|Pres|[Cc]orp|[Ee]x|[Cc]onn|[Dd]ept|[Ll]tda|[Mm]in|[Mm]ax|[Gg]ovt|[Rr]etd|Ing|lb|lbf|ft|c\.?[\s\u00A0]*f|vs|dia|lbs|\d+-(:?oz|kc|in|h[rp]|ml)|M?sec)\.[\s\u00A0]
[^\p{Lu}]|I
\b(hr)\.[\s\u00A0]
[^\p{Lu}]|I
\b([Vv]ol|[Ff]ig|[Dd]ef|[Ee]q|[Ll]em|[Pp]rop|[Tt]hm)s?\.[\s\u00A0]
\p{N}|[IXV]+
\b([Ff]ig|[Dd]ef|[Ee]q|[Ll]em|[Pp]rop|[Tt]hm)s?\.[\s\u00A0]
\(\p{N}\)
(…|\.\.\.)[\s\u00A0]?\)[\s\u00A0]
[^\p{P}]
[?!.…]["”]\)[\s\u00A0]
[a-z].*
(…|\.\.\.)[\s\u00A0]?\?\)[\s\u00A0]
[^\p{P}]
\be\.g\.[\s\u00A0]
\b[Vv]s\.[\s\u00A0]
\b(pp|PP)\.[\s\u00A0]
\be[sx]p\.[\s\u00A0]
\b[Ee]tc\.[\s\u00A0]
[^\p{Lu}]
\b([Bb]tw|BTW)\.[\s\u00A0]
\bJan\.[\s\u00A0]
\bFeb\.[\s\u00A0]
\bMar\.[\s\u00A0]
\bApr\.[\s\u00A0]
\bJu[nl]\.[\s\u00A0]
\bAug\.[\s\u00A0]
\bSept?\.[\s\u00A0]
\bOct\.[\s\u00A0]
\bNov\.[\s\u00A0]
\bDec\.[\s\u00A0]
(?i)FRITZ!
(?i)Box
ID.
3|4|Buzz|Crozz
\bP[Hh]\.?[\s\u00A0]?[Dd]\.[\s\u00A0]
\b(P[hH][dD]|BSc|BEng|BComp|BArch|MSc|MEng|MComp)\.[\s\u00A0]
\bLL\.[\s\u00A0]?[BMD]\.[\s\u00A0]
\b[BM]\.[\s\u00A0]?
Eng\.?
\bLL\.[\s\u00A0]?
[BMD]\.?
\b[BM]\.[\s\u00A0]?
Sc\.?
\b[BM]\.[\s\u00A0]?
Comp?\.?
\b[BM]\.[\s\u00A0]?
Arch\.?
\b[BM]\.?[\s\u00A0]?(Sc|Eng|Comp|Arch)\.[\s\u00A0]
\bet\b[\s\u00A0]\bal\.[\s\u00A0]
\b(a(?:bbrev|uth|bl|bsol|bstr|cc|ccus|dv|dvb|dvs|gst|lt|phet|pp|ppos|cc|dj|djs|rch|rt|ttrib)|A(?:bbrev|uth|bd|berd|berdeensh|bol|borig|bp|br|bridg|bridgem|bsol|bst|bstr|cad|cc|ccept|ccomm|ccompl|ccs|cct|ccts|chievem|dd|ddit|ddr|dm|dmin|dmir|dmon|dmonit|dv|dvancem|dvert|dvoc|dvt|dvts|erodynam|eronaut|ff|ffect|fr|gric|lch|lg|lleg|llit|lm|lph|mer|nal|nalyt|nat|nc|necd|ng|ngl|nim|nn|nniv|nnot|nsw|nt|nthrop|nthropol|ntiq|poc|pol|pp|ppl|pplic|rch|rchaeol|rchipel|rchit|rgt|rith|rithm|rrangem|rtic|rtific|rtill|ssemb|ssoc|ssyriol|str|strol|stron|stronaut|tt|ttrib|ustral|uth|utobiog|utobiogr|yrsh|rab)|B(?:acteriol|edford|edfordsh|elg|erks|erksh|erw|erwicksh|ibliogr|iochem|iog|iogr|iol|ks|ord|ot|raz|rit|ucks|uild|ull|ur)|b(?:ef|etw)|c(?:ent|ollect|olloq|ompar|ompl|onc|oncr|omp|onj|ons|onst|ontempt|orresp|pd|ontr)|C(?:ontradict|ontrib|ontrov|onv|onvent|onversat|onvoc|ornw|oron|orr|orresp|ounc|ourtsh|raniol|raniom|rim|rit|rt|rts|ryptogr|rystallogr|umb|umberld|umbld|ycl|ytol|ollect|onn|al|alc|alend|alif|alligr|amb|ambr|ampanol|anad|anterb|artogr|atal|atech|ath|ent|eram|ert|ertif|hamb|har|harac|has|hem|hesh|hr|hron|hronol|hrons|inematogr|irc|lass|lassif|limatol|lin|oll|olloq|om|omb|ombs|omm|ommandm|ommend|ommerc|ommiss|ommonw|ommunic|omp|ompan|ompar|ompend|ompl|ompos|onc|onch|oncl|onf|onfid|onfl|onfut|ongr|ongreg|ongress|onsc|onsecr|onsid|onsol|onstit|onstr|ontemp|ontempl|ontend|ontent|ontin)|d(?:at|em|ial|im|yslog|ef|eriv|erog)|D(?:au|eb|eclar|ed|ef|eliv|emonstr|ep|epred|epredat|erbysh|escr|evel|evonsh|ial|ict|iffic|irect|is|isc|iscipl|iscov|iscrim|iscuss|iss|istemp|istill|istrib|iv|ivers|oc|octr|omest|urh)|e(?:tym|tymol|uphem|xc|ast|llipt|mph|rron)|E(?:val|vang|ven|vid|vol|xalt|xam|xch|xec|xerc|xhib|xped|xper|xplan|xplic|xplor|xpos|tymol|ccl|ccles|col|con|din|dinb|duc|dw|gypt|gyptol|lectr|lectro-magn|lectro-physiol|lem|liz|lizab|mb|mbryol|ncycl|ng|ngin|nglishw|nq|nt|nthus|ntom|ntomol|nzymol|pil|pisc|pist|pit|quip|ss|ssent|stabl|thnol)|f(?:em|req|ut|am|amil)|F(?:ifesh|ootpr|orfarsh|ortif|ortn|ound|ragm|ratern|riendsh|und|urnit|ab|am|arew)|G(?:ard|astron|az|eo|eog|eogr|eol|eom|eomorphol|er|lac|lasg|los|loss|louc|loucestersh|osp|ram|ynaecol)|g(?:erund|en)|H(?:aematol|ampsh|andbk|ants|eb|en|er|erb|eref|ereford|erefordsh|ertfordsh|ierogl|ist|istol|om|orol|ort|osp|ouseh|ousek|usb|ydraul|ydrol)|hist|I(?:nd|ndustr|nfl|nnoc|norg|nq|nst|ntell|ntellect|nterc|nterl|nternat|nterpr|chth|cthyol|deol|dol|llustr|mag|mpr|naug|nclos|nd|nstr|tal|ntro|ntrod|nv|nvent|nvertebr|nvestig|nvestm|nvoc|rel|mmunol)|i(?:nt|nterj|nterrog|ntr|ntrans|mp|mperf|mpers|mpf|mprop|nstr|nd|ndef|ndic|ndir|nfin|nfl|ron|rreg|mit)|J(?:ahrb|ap|as|rnl|rnls|urisd|urisdict|urispr|ustif|ustific)|joc|K(?:ent|ingd|nowl|pr)|L(?:ab|anc|ancash|ancs|ang|angs|at|d|ds|ect|eechd|eg|eicest|eicester|eicestersh|eics|et|ett|ex|ibr|imnol|incolnsh|incs|ing|inn|it|ithogr|ithol|iturg|ond)|m(?:asc|ed|etaphor|idl|ispr|od)|M(?:ach|ag|agn|an|anagem|anch|anip|anuf|ath|eas|easurem|ech|ed|edit|em|erc|erch|etall|etallif|etallogr|etamorph|etaph|eteorol|eth|etrop|ex|ich|icrobiol|icrosc|il|ilit|in|ineral|isc|iscell|od|onum|orphol|SS|tg|unic|unif|unim|us|yst|yth|ythol)|n(?:once-wd|orth|om)|N(?:arr|arrat|at|aut|av|avig|eighb|erv|eurol|eurosurg|ewc|ewspr|onconf|orf|orthamptonsh|orthants|orthumb|orthumbld|orthumbr|orw|orweg|otts|ucl|umism|on-conf)|o(?:ccas|pp|rig|bj|bl|bs)|O(?:bs|bserv|bstet|bstetr|ccas|ccup|ccurr|ceanogr|ff|ffic|kla|nt|phthalm|phthalmol|ppress|pt|rac|rd|rg|rig|rkn|rnith|rnithol|rthogr|utl|xf|xfordsh|xon|bed|bj)|p(?:ass|erf|ers|ersonif|honet|hr|op|lur|oet|ref|rep|riv|rob|oss|pl|ple|ples|rec|red|redic|ron|ronunc|rop|rov|ropr|seudo-arch|seudo-dial|seudo-Sc|erh|res)|P(?:eriodontol|redict|rerog|sych|sychoanal|sychoanalyt|sychol|sychopathol|ubl|urg|erf|alaeobot|alaeogr|alaeont|alaeontol|araphr|arasitol|arl|arnass|ath|athol|eculat|enins|ers|ersec|erthsh|etrogr|etrol|harm|harmaceut|harmacol|hil|hilad|hilol|hilos|hoen|honol|hotog|hotogr|hrenol|hys|hysiogr|hysiol|ict|oet|ol|olit|olytechn|op|orc|ort|osth|ostm|ott|ract|ref|reh|rehist|resb|reserv|rim|rinc|rint|robab|robl|roc|rod|rol|rov|rovid|rovinc|rovis|ronunc|rop|ros)|Qld|q(?:uot|uots)|r(?:edupl|eg|epr|het|efash|efl|el)|R(?:adiol|eas|eb|ebell|ec|eclam|ecoll|edempt|ef|efl|efus|efut|eg|egic|egist|egr|el|elig|eminisc|emonstr|enfrewsh|eprod|ept|epub|es|esid|et|etrosp|evol|het|ich|om|oxb|oy|udim|uss)|s(?:ing|outh|pec|tr|ubj|ubjunct|ubord|ubseq|ubst|uff|uperl|yll)|S(?:ubj|uff|ubscr|ubscript|uppl|upplic|uppress|urg|urv|ymmetr|ymp|yst|pan|ask|at|ax|cand|ch|ci|cot|cotl|cript|culpt|eismol|el|elect|er|erm|ess|ettlem|ev|hakes|haks|heph|hetl|hropsh|oc|ociol|om|onn|pec|pecif|pecim|pectrosc|taff|tafford|taffordsh|taffs|tand|tat|tatist|tratigr|truct|tud)|t(?:echn|rans|ransf|ransl)|T(?:ransl|ransubstant|rav|reas|reat|reatm|rib|rig|rigonom|rop|roub|roubl|ypog|ypogr|axon|rans|echn|echnol|el|elecomm|elegr|eleph|eratol|erminol|errestr|est|extbk|heat|heatr|heol|heoret|hermonucl|hes|opogr|rag)|U(?:niv|rin)|u(?:nkn|nstr|lt|su)|U(?:nnat|noffic|tilit)|V(?:ac|aledict)|v(?:ar|arr|ars|bl|bs|ulg)|V(?:eg|enet|ertebr|et|ic|ict|ind|indic|irg|irol|oc|ocab|ol|oy|ulg)|W(?:estm|estmld|estmorld|estmrld|ill|ilts|iltsh|is|isd|kly|ks|onderf|orc|orcestersh|orcs|rit|arwicksh)|west|Y(?:earbk|ng|orks|orksh|rs)|Z(?:eitschr|oogeogr|ool))\.\b
\b(Atty|Sg?t|[SG]en|Ft|Gov|Hon|Prof|Mr?s|Mt|[DMJS]r|Col|Maj|L(ieu)?t|Brig|Capt|Cmdr|Cmnd|Revd?|Rep)\.[[\s\u00A0]\u00A0]
\b(Atty|Sg?t|[SG]en|Gov|Hon|Prof|Mr?s|[DMJS]r|Col|Maj|L(ieu)?t|Brig|Capt|Cmdr|Cmnd|Revd?|Rep)\.[\s\u00A0][A-Z]\.[\s\u00A0]
\b(Drs|Messrs|Mmes)\.[\s\u00A0]
(and[\s\u00A0])|\p{Lu}\p{Ll}+
\bcf\.[\s\u00A0]
\bI(nc|NC)\.[\s\u00A0]
\b[cC]orp\.[\s\u00A0]
\b[Rr]eg\.[\s\u00A0]
\bBros\.[\s\u00A0]
\bDist\.[\s\u00A0]
\bCo\.[\s\u00A0]
\bo'clock[\s\u00A0]
\bfo'c'sle[\s\u00A0]
\bLtd\.[\s\u00A0]
\p{Ll}+
[\[\(]*…[\]\)]*
\p{Ll}
\p{Ps}[!?]+\p{Pe}
[\.!?…]+\p{Pe}
\p{Ll}
["”'’][\s\u00A0]*
[\s\u00A0]*\p{Ll}
['"„][\.!?…]['"”][\s\u00A0]
\b\p{L}\.[\s\u00A0]
\p{L}\.[\s\u00A0]
\b\p{L}\.
\p{L}\.
\p{Lu}\p{L}+[\s\u00A0]v\.[\s\u00A0]
\p{Lu}\p{L}+
[^,][\s\u00A0]\p{L}{2}\.[\s\u00A0]
\p{N}+\)[\s\u00A0]
\bOK\.[\s\u00A0]
\p{Ll}+
[\.\s\u00A0](?!(on|it|of|to|be|by|at|he|we|so|do|if|up|my|me|us|go|am))\p{L}{1,2}\.[\s\u00A0]
[\p{N}\p{Ll}]
[\[\(]*\.\.\.[\]\)]*
[^\p{Lu}]
\b\p{Lu}\.[\s\u00A0]\p{Lu}\.[\s\u00A0]
\b\p{Lu}\.\p{Lu}\.[\s\u00A0]
[^\.][\s\u00A0][A-Z]\.[\s\u00A0]
\b(:?Blvd|Ave|Mts?)\.[\s\u00A0]
\p{Ll}+
\b(?:Kan|Ill|M[ai]ss)\.[\s\u00A0]
\p{Ll}+
\(\p{Ll}+\.[\s\u00A0]
i\.e\.[\s\u00A0]
[\.!?…][\u00BB\u2019\u201D\u203A"'\p{Pe}\u0002¹²³]*[\s\u00A0]
[\.!?…]['"\u00BB\u2019\u201D\u203A\p{Pe}\u0002]*
\p{Lu}[^\p{Lu}]
[\s\u00A0]\p{L}[\.!?…][\s\u00A0]
\p{Lu}\p{Ll}
\b\d+\.\s
\p{Ll}|\p{Lu}{2,}
["”']\s*
\s*\p{Ll}
['"„][\.!?…]['"”]\s
\b\p{L}\.\s
\p{L}\.\s
\b\p{L}\.
\p{L}\.
[\.\s]\p{L}{1,2}\.\s
[\p{N}\p{Ll}]
[!?]+\p{Pe}
\p{Ll}
[\p{Ps}][!?]+[\p{Pe}]
[\[\(]*\.\.\.[\]\)]*
[^\p{Lu}]
\b(etc|șamd)\.\s
[A-Z]
\b(pag|leg|art)\.\s
\b(ian|febr?|mart?|apr|iu[nl]|aug|sept?|oct|nov|dec)\.\s
[^\p{Lu}]
\bdpdv\.\s
\b(etc|șamd)\.\s
\b(M)\.
Ap\.N\.\s
\b(M)\.Ap\.
N\.\s
\b([Dd]l|[Dd]-na|[Dd]vs|[Pp]t)\.\s
\b([Dd]l|[Dd]-na|[Dd]vs|[Pp]t)\.\s[A-Z]\.\s
[\[\(]*\.\.\.[\]\)]*
\p{Ll}
[\[\(]*…[\]\)]*
\p{Ll}
[\.!?…]['"\u00BB\u2019\u201D\u203A\u0002¹²³]*\s
[\.!?…]['»"”\p{Pe}]*
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?…]\s
\p{Lu}\p{Ll}
\sart\.\s
[IVX]+[ .]
\s([a-z]\.){2,10}\s
[ ]is[.][ ]
[0-9]\.($|[ ])
(^| )O\.\s
([A-Z][a-z]{1,3}[ ,:;.!?]|Indië|Wanneer|Kunnen|Sorry)
\sEd[.]\s
([A-Z][a-z]{1,3}|Wanneer|Misschien|Daarna|Zoals|Zelfs|Bedankt|Zullen|Vooral|Volgens|Vervolgens)(\s|[,:;])
\b(sp|SP)
\.[aA]\b
\s[.]
[Nn][Ee][Tt](\b|-)
[.?!][’'"]
[a-z]
\b(https?|ftp|file|chrome|chromium|android|(chrome|moz)\-extension):///?[A-Za-z0-9\-]+\.
[A-Za-z0-9\-]+(\.|\b)
\b[A-Za-z0-9\-]+\.
[A-Za-z0-9\-]+\.(com|net|org|info|de|es|edu|co|eu|nl|io|cn|uk|gov|biz|ca|tk|ru|br|jp|pl)(\.|\b)
\b(blz|pag|fig)\.\s
[0-9]
\b(enz|etc|zat|ambt|al|ver|art|wed|lab|bv|Bros)\.\s
\p{Ll}
\s(la|do|del?)\sMar\.\s
\b(Ge?n|Ex|Le?v|Nu?m|D(eu)?t|Jo?z|Ri|R[ei]cht|Sa?m|Ko?n|Kr[on]{0,2}|Neh?|Est?|Jb|Ps|Spr?|Pr[ed]{0,2}|H(oog)?l|Je?s|Je?r|Kl(aagl)?|Ez(ech)?|Da?n|Ho?s|Jl|Am|Ob|Mc|Mi[ch]{0,2}|Nah?|Hk|Hab|Zf|[SZ]ef|Ha?g|Zc|Zach|Ma?l|Ma?t|Mk|Mar|Lk|Jh|H(an)?d|Ro?m|Kor|Ga?l|Ef|Fp|Fil|Ko|[CK]ol|Th|Th?e[s]{1,2}|Tm|Ti?t|Fm|Fil(em)?|Hb|Hebr?|Jk|Ja[ck]|Pe?tr?|Joh|Jud|Op(enb)?|Wijsh|Tob|Sir|Bar|Makk)\.\s
\b(Drs|Art|Afr|Am|Ar|Br|Cie|Comp|Dhr|(Prof\.)?[Dd]r|Em|Fa|Kon|Stb)\.\s
\p{Lu}
\b(Stb)\.\s
[0-9]
\b([Mm]ej|[Mm]evr|[Mm]rs|[Mm]s|[Mm]gr|[Mm]w|Ndl|Ned|Nl|No|Prof|[Ss]ecr|Chr|Jac|[Ww]ed|Zr)\.\s
\b(Sr|St|Ued|Vz|aanh|aanw|aardew|aardr)\.\s
\b(abs|abstr|adj|adm|[Aa]fb|[Aa]fd|afk|afl|milj|zgn|plv|bvb|afm|evt|exp|vs)\.\s
\b(ald|alg|amb|anat|antrop|apoth)\.\s
\seen\sprof\.\s
\p{Lu}
\b(alc|bro|opm|acc)\.\s
\b(arch|archeolbc|bep|betr|bez|bibl|bijl|[Bb]ijv)\.\s
\b(bijz|bw|ca|cat|centr|cf|cfr|cmpl)\.\s
\b(conf|ct|dal|derg|dhr|dir|div|dra|drs|ds)\.\s
\b([Ee]d|em|ev|[Ee]xcl|[Ff]a|[Ff]am|[fF]ig|fin|fl|fr)\.\s
\b(geb|[Gg]em|get|gld|id|[Ii]ncl|ind|inf|ing|intern|[Ss]ec|inz|ir|jhr|jkvr)\.\s
\s(tel|red|min)\.\s
[A-Z]
\.(nl|be|com)\.\s
\b(jl|jr|kr|kt|lic|ll|lt|lw|max|[Mm]evr|mi|[Mm]in|mld)\.\s
\b(mln|[Mm]r|[Mm]w|nl|no|nr|nrs|ob|obl|ong|onov)\.\s
\b(opm|org|ov|[Pp]ag|par|penn|([1-3][\.e]?)[\s]?pers|plm|plv)\.\s
\b(prov|pseud|psych|qty|red|ref|resp|soc|st|tab|tel|temp|prof|tk)\.\s
\sgraden C\.\s
[A-Z]
\svitamine [A-Z]\.\s
[A-Z]
°C\.\s
[A-Z][a-z]
[A-Z]&[A-Z]\.\s
[A-Z][a-z]
\b([A-Z]|Adr|Chr|Fr|Fred|IJ|Jac|Joh|Ph|St|Th|Tj|v|v\.(\s)?d)\.(\s)?
\p{Lu}
\b[vn]\.\s
Chr
\b(uitsl|vgl|vnl|vnw|voorz|ww|zat|[Zz]elfst|zgn?)\.\s
\p{Ll}
\b(mm|cm|km|ml|mg|kg|h|kW|kg|mW)\.\s
\p{Ll}|\p{Lu}{2,}
\b(mm|cm|km|ml|mg|kg|h|kW|kg|mW)\.\s
[\[\(]*…[\]\)]*
\p{Ll}
\p{Ps}[!?]+\p{Pe}
[\.!?…]+\p{Pe}
\p{Ll}
["”']\s*
\s*\p{Ll}
['"„][\.!?…]['"”]\s
\b\p{L}\.\s
\p{L}\.\s
\set al\.\s
\spa\.\s
[0-9]
\sop\.\s
[0-9]|cit\.
\soa\.\s
[a-z]
\sal\.\s
[0-9]
\s((is|op|in|af|ik|ze|om|me|je|na|nu|al|ja|VS|EU|er|we|tv|he|ga|hè|hé|TV|as|ei|SP|pc|wc|PC|IS|NS|ok|AD|OK|at|OM|cd|VN|it|EK|In|pa|AZ|up|IT|FM|VI|ui|la|CD|CV|pr|ie|cv|WW|GB|Jo|Aa|UK|HD|oa|VU))\.\s
\b\p{L}\.
\p{L}\.
\sik\.\s
ik\s
[\.\s]\p{L}{1,2}\.\s
[\p{N}\p{Ll}]
[\[\(]*\.\.\.[\]\)]*
[^\p{Lu}]
\b\p{Lu}\.\s\p{Lu}\.\s
\b\p{Lu}\.\p{Lu}\.\s
\s(op)\sX\.\s
[^\.]\s[A-Z]\.\s
\.\p{Lu}\p{Ll}\.\s?
\p{Lu}[^\p{Lu}]
\b\d+\.\s
\p{Ll}|\p{Lu}{2,}
[.!?…][’'"]\s
[a-z]
[.][.]\s
[a-z]
SP[.]
A
Warner Bros\.
[a-z]
\s'[2-9][.]\s
(^|\s)[A-Z].+!\s
[a-z]
\s[A-Z].+z\.\s
[a-z]
\sart\.\s
[0-9]
\b(jan|mrt|mar|jun|jul|aug|sept|okt|sep|spt|nov|dec|.*opp)\.\s
[a-z]
Groen!\s
[a-z]
[.!?…][’'"\u00BB\u2019\u201D\u203A\u00AB\p{Pe}\u0002¹²³]*\s
[.!?…][’'"\u00BB\u2019\u201D\u203A\u00AB\p{Pe}\u0002]*
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?…]\s
\p{Lu}\p{Ll}
\p{L}!
[^ ]
\)
\.
\.
\)
\)\.
[A-Z]
\.\)
[A-Z]
\bmax\.\s
\p{Ll}
[?!.]['"\u00BB\u2019\u201D\u203A\u00AB\p{Pe}\u0002]\s
[A-Z][a-z]
[?!.]\s
['"\u00BB\u2019\u201D\u203A\u00AB\p{Pe}\u0002][A-Z][a-z]
"[A-Z][.]\s
[a-z]
[A-Z][a-z].*sz[.]\s
[a-z]
De n[.]\s
[a-z]|[XIV]
[A-Z]{2,5}[.]
[A-Z]
\.\.
" [a-z]
\sBTW\.
\p{Ll}
\b(Bc|Mgr|RNDr|PharmDr|PhDr|JUDr|PaedDr|ThDr|Ing|MUDr|MDDr|MVDr|Dr|ThLic|PhD|ArtD|ThDr|Dr|DrSc|CSs|prof)\.\s
\b([Oo]br|[Čč])\.\s
\p{N}
\babl\.\s
\babsol\.\s
\badj\.\s
\badmin\.\s
\b[Aa]dr\.\s
\badv\.\s
\badvok\.\s
\bafr\.\s
\bak\.\s
\bakad\.\s
\bakc\.\s
\bakuz\.\s
\bet\b\s\bal\.\s
\bal\.\s
\balch\.\s
\bamer\.\s
\banat\.\s
\b[Aa]ngl\.\s
\banglosas\.\s
\banorg\.\s
\bap\.\s
\bapod\.\s
\barch\.\s
\barcheol\.\s
\barchit\.\s
\barg\.\s
\bart\.\s
\bastr\.\s
\bastrol\.\s
\bastron\.\s
\batp\.\s
\batď\.\s
\b[Aa]ustr\.\s
\baut\.\s
\b[Bb]elg\.\s
\b[Bb]ibl\.\s
\bbiol\.\s
\bbot\.\s
\bbud\.\s
\bbás\.\s
\bbýv\.\s
\bcest\.\s
\bchem\.\s
\bcirk\.\s
\bcsl\.\s
\b[Čč]s\.\s
\bdat\.\s
\bdep\.\s
\bdet\.\s
\bdial\.\s
\bdiaľ\.\s
\bdipl\.\s
\bdistrib\.\s
\bdokl\.\s
\bdosl\.\s
\bdopr\.\s
\bdram\.\s
\bduš\.\s
\bdv\.\s
\bdvojčl\.\s
\bdór\.\s
\bekol\.\s
\bekon\.\s
\bel\.\s
\belektr\.\s
\belektrotech\.\s
\benerget\.\s
\bepic\.\s
\best\.\s
\betc\.\s
\betonym\.\s
\beufem\.\s
\b[Ee]uróp\.\s
\bev\.\s
\bevid\.\s
\bexpr\.\s
\bfa\.\s
\bfam\.\s
\bfarm\.\s
\bfem\.\s
\bfeud\.\s
\bfil\.\s
\bfilat\.\s
\bfiloz\.\s
\bfi\.\s
\bfon\.\s
\bform\.\s
\bfot\.\s
\b[Ff]r\.\s
\b[Ff]ranc\.\s
\bfraz\.\s
\bfut\.\s
\bfyz\.\s
\bfyziol\.\s
\bgarb\.\s
\bgen\.\s
\bgenet\.\s
\bgenpor\.\s
\bgeod\.\s
\bgeogr\.\s
\bgeol\.\s
\bgeom\.\s
\bgerm\.\s
\b[Gg]r\.\s
\b[Gg]réc\.\s
\bgréckokat\.\s
\bhebr\.\s
\bherald\.\s
\bhist\.\s
\bhl\.\s
\bhlav\.\s
\bhosp\.\s
\bhromad\.\s
\bhud\.\s
\bhypok\.\s
\bident\.\s
\bi\.?e\.\s
\bident\.\s
\bimp\.\s
\bimpf\.\s
\bindoeur\.\s
\binf\.\s
\binform\.\s
\binstr\.\s
\bint\.\s
\binterj\.\s
\binšt\.\s
\binštr\.\s
\biron\.\s
\b[Jj]ap\.\s
\bjaz\.\s
\bjedn\.\s
\bjuhoamer\.\s
\bjuhových\.\s
\bjuhozáp\.\s
\bjuž\.\s
\b[Kk]anad\.\s
\bkanc\.\s
\bkapit\.\s
\bkpt\.\s
\bkart\.\s
\bkatastr\.\s
\bknih\.\s
\bkniž\.\s
\bkomp\.\s
\bkonj\.\s
\bkonkr\.\s
\bkozmet\.\s
\bkrajč\.\s
\bkresť\.\s
\bkt\.\s
\bkuch\.\s
\blat\.\s
\blatinskoamer\.\s
\blek\.\s
\blex\.\s
\blingv\.\s
\blit\.\s
\blitur\.\s
\blog\.\s
\blok\.\s
\b[Mm]ax\.\s
\b[Mm]aď\.\s
\bmedzinár\.\s
\bmest\.\s
\bmetr\.\s
\b[Mm]il\.\s
\b[Mm]in\.\s
\bminer\.\s
\bml\.\s
\bmld\.\s
\bmn\.\s
\bmod\.\s
\bmytol\.\s
\bnapr\.\s
\b[Nn]ar\.\s
\bnasl\.\s
\bnedok\.\s
\bneg\.\s
\bnegat\.\s
\bneklas\.\s
\b[Nn]em\.\s
\bneodb\.\s
\bneos\.\s
\bneskl\.\s
\bnesklon\.\s
\bnespis\.\s
\bnespráv\.\s
\bneved\.\s
\bnež\.\s
\bniekt\.\s
\bniž\.\s
\bnom\.\s
\bnáb\.\s
\bnákl\.\s
\bnámor\.\s
\bnár\.\s
\bobch\.\s
\bobj\.\s
\bobv\.\s
\bobyč\.\s
\bobč\.\s
\bobčian\.\s
\bodb\.\s
\bodd\.\s
\bods\.\s
\bojed\.\s
\b[Oo]kr\.\s
\bopt\.\s
\bopyt\.\s
\borg\.\s
\bos\.\s
\bosob\.\s
\bot\.\s
\bovoc\.\s
\bpar\.\s
\bpart\.\s
\bpejor\.\s
\bpers\.\s
\b(pf|Pf|P\.f|p\.f)\.\s
\bpl\.\s
\bPlk\.\s
\bpod\.\s
\bpodst\.\s
\bpokl\.\s
\bpolit\.\s
\bpolitol\.\s
\bpolygr\.\s
\bpomn\.\s
\bpopl\.\s
\bpor\.\s
\bporad\.\s
\bporov\.\s
\bposch\.\s
\bpotrav\.\s
\bpouž\.\s
\bpoz\.\s
\bpozit\.\s
\bpoľ\.\s
\bpoľno\.\s
\bpoľnohosp\.\s
\bpoľov\.\s
\bpošt\.\s
\bpož\.\s
\bprac\.\s
\bpredl\.\s
\bpren\.\s
\bprep\.\s
\bpreuk\.\s
\b[Pp]riezv\.\s
\bprivl\.\s
\bprof\.\s
\bpráv\.\s
\bpríd\.\s
\bpríj\.\s
\bprík\.\s
\bpríp\.\s
\bprír\.\s
\bprísl\.\s
\bpríslov\.\s
\bpríč\.\s
\bpsych\.\s
\bpubl\.\s
\bpís\.\s
\bpísm\.\s
\bpôv\.\s
\brefl\.\s
\breg\.\s
\brep\.\s
\bresp\.\s
\brozk\.\s
\brozlič\.\s
\brozpráv\.\s
\b[Rr]oč\.\s
\bryb\.\s
\brádiotech\.\s
\brím\.\s
\bsamohl\.\s
\bsemest\.\s
\bsev\.\s
\bseveroamer\.\s
\bseverových\.\s
\bseverozáp\.\s
\bsg\.\s
\bskr\.\s
\bskup\.\s
\bsl\.\s
\bSloven\.\s
\bsoc\.\s
\bsoch\.\s
\bsociol\.\s
\bsp\.\s
\b[Ss]pol\.\s
\bspoloč\.\s
\bspoluhl\.\s
\bspráv\.\s
\bspôs\.\s
\bst\.\s
\bstar\.\s
\bstarogréc\.\s
\bstarorím\.\s
\bs\.r\.o\.\s
\bstol\.\s
\bstor\.\s
\bstr\.\s
\bstredoamer\.\s
\bstredoškol\.\s
\bsubj\.\s
\bsubst\.\s
\bsuperl\.\s
\bsv\.\s
\bsz\.\s
\bsúkr\.\s
\bsúp\.\s
\bsúvzť\.\s
\b[Tt]al\.\s
\btech\.\s
\b[Tt]el\.\s
\btelef\.\s
\bteles\.\s
\btelev\.\s
\bteol\.\s
\btrans\.\s
\bturist\.\s
\btuzem\.\s
\btypogr\.\s
\btzn\.\s
\btzv\.\s
\bukaz\.\s
\b[Uu]l\.\s
\bumel\.\s
\buniv\.\s
\bust\.\s
\bved\.\s
\bvedľ\.\s
\bverb\.\s
\bveter\.\s
\bvin\.\s
\bviď\.\s
\bvl\.\s
\bvod\.\s
\bvodohosp\.\s
\bp?nl\.\s
\bvulg\.\s
\bvyj\.\s
\bvys\.\s
\bvysokoškol\.\s
\bvzťaž\.\s
\bvôb\.\s
\bvých\.\s
\bvýd\.\s
\bvýrob\.\s
\bvýsk\.\s
\bvýsl\.\s
\bvýtv\.\s
\bvýtvar\.\s
\bvýzn\.\s
\bvčel\.\s
\bvš\.\s
\bvšeob\.\s
\bzahr\.\s
\bzar\.\s
\bzariad\.\s
\bzast\.\s
\bzastar\.\s
\bzastaráv\.\s
\bzb\.\s
\bzdravot\.\s
\bzdruž\.\s
\bzjemn\.\s
\bzlat\.\s
\b[Zz]n\.\s
\bzool\.\s
\bzr\.\s
\bzried\.\s
\bzv\.\s
\bzáhr\.\s
\bzák\.\s
\bzákl\.\s
\bzám\.\s
\bzáp\.\s
\bzápadoeur\.\s
\bzázn\.\s
\bázij\.\s
\búzem\.\s
\búčt\.\s
\bčast\.\s
\b[Čč]es\.\s
\bčl\.\s
\bčísl\.\s
\bživ\.\s
\bpr\.\s
\bfak\.\s
\b[Ss]lov\.\s
\p{Ll}
\bKr\.\s
\bp\.n\.l\.\s
[^\p{Lu}]
\b[Jj]r\.\s
\b(P\.\s?S|p\.\s?s|P\.\s?s)\.\s
\b\d+\.\s
\p{Ll}|\p{Lu}{2,}
\p{Ps}[!?]+\p{Pe}
[\[\(]*…[\]\)]*
\p{Ll}
[\.!?…]+\p{Pe}
\p{Ll}
["”']\s*
\s*\p{Ll}
['"„][\.!?…]['"”]\s
\b\p{L}\.\s
\p{L}\.\s
\b\p{L}\.
\p{L}\.
[\.\s]\p{L}{1,2}\.\s
[\p{N}\p{Ll}]
[\[\(]*\.\.\.[\]\)]*
[^\p{Lu}]
\b\p{Lu}\.\s\p{Lu}\.\s
\b\p{Lu}\.\p{Lu}\.\s
[^\.]\s[A-Z]\.\s
\b\p{Lu}\p{Ll}\.\s?
\p{Lu}[^\p{Lu}]
[\.\s]\p{L}{1,2}\.\s
[\p{N}\p{Ll}]
[\.!?…][\u00BB\u2019\u201D\u203A"'\p{Pe}\u0002¹²³]*\s
[\.!?…]['"\u00BB\u2019\u201D\u203A\p{Pe}\u0002]*
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?…]\s
\p{Lu}\p{Ll}
\b[nN]o\.\s
\p{N}
\b[nN][rR]\.\s
\p{N}
\b\p{N}+\.\s
\b(janúar|febrúar|mars|apríl|maí|júní|júlí|ágúst|september|október|nóvember|desember)
\b\p{N}+\.\s
\b(jan|feb|mar|apr|maí|jún|júl|ágú|sep|sept|okt|nóv|des)
\b[a-z[^íáóæ]]\.\s
\b\p{L}\.
\p{L}\.
\bab\.fn\.\s
\ba\.fn\.\s
\bafs\.\s
\bal\.\s
\balm\.\s
\balg\.\s
\bandh\.\s
\bath\.\s
\baths\.\s
\batr\.\s
\bao\.\s
\bau\.\s
\baukaf\.\s
\báfn\.\s
\báhrl\.s\.\s
\báhrs\.\s
\bákv\.gr\.\s
\bákv\.\s
\bbh\.\s
\bbls\.\s
\bdr\.\s
\be\.Kr\.\s
\bet\.\s
\bef\.\s
\befn\.\s
\bennfr\.\s
\beink\.\s
\bend\.\s
\be\.st\.\s
\berl\.\s
\bfél\.\s
\bfskj\.\s
\bfh\.\s
\bf\.hl\.\s
\bfísl\.\s
\b[A-ZÁ-Þ][a-zá-þ]+fj\.\s
\bfl\.\s
\bfn\.\s
\bfo\.\s
\bforl\.\s
\bfrb\.\s
\bfrl\.\s
\bfrh\.\s
\bfrt\.\s
\bfsl\.\s
\bfsh\.\s
\bfs\.\s
\bfsk\.\s
\bfst\.\s
\bf\.Kr\.\s
\bft\.\s
\bfv\.\s
\bfyrrn\.\s
\bfyrrv\.\s
\bgerm\.\s
\bgm\.\s
\bgr\.\s
\bhdl\.\s
\bhdr\.\s
\bhf\.\s
\bhl\.\s
\bhlsk\.\s
\bhljsk\.\s
\bhljv\.\s
\bhljóðv\.\s
\bhr\.\s
\b[A-ZÁ-Þ][a-zá-þ]+hr\.\s
\bhv\.\s
\bhvk\.\s
\bholl\.\s
\bHos\.\s
\bhöf\.\s
\bhk\.\s
\bhrl\.\s
\bísl\.\s
\bkaf\.\s
\bkap\.\s
\bKhöfn\.\s
\bkk\.\s
\bkg\.\s
\bkk\.\s
\bkm\.\s
\bkl\.\s
\bklst\.\s
\bkr\.\s
\bkt\.\s
\bkgúrsk\.\s
\bkvk\.\s
\bleturbr\.\s
\blh\.\s
\blh\.nt\.\s
\blh\.þt\.\s
\blo\.\s
\bltr\.\s
\bmlja\.\s
\bmljó\.\s
\bmillj\.\s
\bmm\.\s
\bmms\.\s
\bm\.fl\.\s
\bmiðm\.\s
\bmgr\.\s
\bmst\.\s
\bmín\.\s
\bnf\.\s
\bnh\.\s
\bnhm\.\s
\bnl\.\s
\bnk\.\s
\bnmgr\.\s
\bno\.\s
\bnúv\.\s
\bnt\.\s
\bo\.áfr\.\s
\bo\.m\.fl\.\s
\bohf\.\s
\bo\.fl\.\s
\bo\.s\.frv\.\s
\bófn\.\s
\bób\.\s
\bóákv\.gr\.\s
\bóákv\.\s
\bpfn\.\s
\bPR\.\s
\bpr\.\s
\bRitstj\.\s
\bRvík\.\s
\bRvk\.\s
\bsamb\.\s
\bsamhlj\.\s
\bsamn\.\s
\bsamn\.\s
\bsbr\.\s
\bsek\.\s
\bsérn\.\s
\bsf\.\s
\bsfn\.\s
\bsh\.\s
\bsfn\.\s
\bsh\.\s
\bs\.hl\.\s
\bsk\.\s
\bskv\.\s
\bsl\.\s
\bsn\.\s
\bso\.\s
\bss\.us\.\s
\bs\.st\.\s
\bsamþ\.\s
\bsbr\.\s
\bshlj\.\s
\bsign\.\s
\bskál\.\s
\bst\.\s
\bst\.s\.\s
\bstk\.\s
\bsþ\.\s
\bteg\.\s
\btbl\.\s
\btfn\.\s
\btl\.\s
\btvíhlj\.\s
\btvt\.\s
\btill\.\s
\bto\.\s
\bumr\.\s
\buh\.\s
\bus\.\s
\buppl\.\s
\bútg\.\s
\bvb\.\s
\bVf\.\s
\bvh\.\s
\bvkf\.\s
\bVl\.\s
\bvl\.\s
\bvlf\.\s
\bvmf\.\s
\b8vo\.\s
\bvsk\.\s
\bvth\.\s
\bþt\.\s
\bþf\.\s
\bþjs\.\s
\bþgf\.\s
\bþlt\.\s
\bþolm\.\s
\bþm\.\s
\bþml\.\s
\bþýð\.\s
[\.!?…][\u00BB\u2019\u201D\u203A"'\p{Pe}\u0002¹²³]*\s
[\.!?…]['"\u00BB\u2019\u201D\u203A\p{Pe}\u0002]*
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?…]\s
\p{Lu}\p{Ll}
\b\d+\.\s
\p{Ll}|\p{Lu}{2,}
\b[А-ЯЁ]\.\s
\b[A-Z]\.\s
\b[А-ЯЁ]\.
[А-ЯЁ][а-яё]+
\b[А-ЯЁ]\.[А-ЯЁ]\.
[А-ЯЁ][а-яё]+
\b\p{L}\.
\p{L}\.
\b[0-9]+(гг|г)\.\s
\b[XVILMC]+(в|вв)\.\s
\b[0-9]+(\.|:)[0-9][0-9]\s
\b[0-9]+(\.|:)[0-9][0-9](\.|:)[0-9][0-9]\s
\b[0-9]+(м|мм|см|дм|л|км|га|кг|т|г|мг)\.\s
\p{Ll}
\b[0-9]+(руб|Руб|тыс|Тыс|трлн|млн|млрд)\.\s
\b[0-9]+
\b(бульв|г|д|доп|др|е|зам|Зам|и|им|инд|исп|Исп)\.\s
\b(англ|в|вв|га|гг|гл|гос|грн|дм|долл|е|ед)\.\s
\p{Ll}
\b(к|кап|кав|кв|кл|кол|комн|куб|л|лиц|лл|м|макс)\.\s
\b(кг|км|коп|л|лл|м|мг|мин|мл|млн|Млн|млрд|Млрд|мм)\.\s
\p{Ll}
\b(н|наб|нач|неуд|нем|ном|о|обл|обр|общ|ок|ост|отл|п|пер|Пер|перераб|пл|пос|пр|пром|просп|Просп|проф|Проф)\.\s
\b(р|ред|Рис|рус|с|сб|св|См|см|сов|соч|соц|спец|ср|ст|стр|т|тел|Тел|тех|тов|тт|туп)\.\s
\p{Ll}
\b(руб|Руб|тыс|Тыс|трлн)\.\s
\p{Ll}
\b(уд|ул|уч|физ|х|хор|э|Эл|эл)\.\s
\b(ч|чел|шт|экз)\.\s
\p{Ll}
['"„“][\.!?…]['"”]\s
[\u00AB][\.!?…][\u00BB]\s
[\[\(]*\.\.\.[\]\)]*
\p{Ll}
[\[\(]*…[\]\)]*
\p{Ll}
["”'\u00BB]\s*
\s*\p{Ll}
[\.!?…]['"\u00BB\u2019\u201D\u203A\u0002¹²³]*\s
\u005D\u005D\s
[\.!?…]['»"”\p{Pe}]*
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?…]\s
\p{Lu}\p{Ll}
\p{L}[\.!?…]\u00A0+\s+
\p{Lu}\p{Ll}
\p{L}[\.!?…]\s+\u00A0+
\p{Lu}\p{Ll}
\u2029
<0\}
\{0>
\d{2}:\d{2}:\d{2},\d{3}\r?\n
\r?\n
\r?\n\s*\r?\n[\t]*
[.!?]\u00A0\r?\n
\b[dD]r\.\s
\bitd\.\s
\bitn\.\s
\b[šŠ]t\.\s
\p{N}
[\[\(]*\.\.\.[\]\)]*
\p{Ll}
[\[\(]*…[\]\)]*
\p{Ll}
['"„][\.!?…]['"”]\s
\bd\.\s
\b[jJ]an\.\s
\b[fF]eb\.\s
\b[mM]ar\.\s
\b[aA]pr\.\s
\b[jJ]u[ln]\.\s
\b[aA]vg\.\s
\b[sS]ept?\.\s
\b[oO]kt\.\s
\b[nN]ov\.\s
\b[dD]ec\.\s
\b[tT]j\.\s
\b[nN]pr\.\s
\b[sS]l\.\s
\b[oO]p\.\s
\b[gG]l\.\s
\b[oO]z\.\s
\bprev\.\s
\bdipl\.\s
\bing\.\s
\b[pP]rim\.\s
\b[cC]f\.\s
\b[0-9]+(\.|:)[0-9][0-9](\.|:)[0-9][0-9]\s
\b[0-3][0-9]+(\.|:)[0-9][0-9](\.|:)[0-9][0-9]\s
\b[0-9]+\.\s
\b[XVILMC]+\.\s
\b[gG]l\.\s
[\.!?…][\u00BB\u2019\u201D\u203A"'\p{Pe}\u0002¹²³]*\s
[\.!?…]['"\u00BB\u2019\u201D\u203A\p{Pe}\u0002]*
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?…]\s
\p{Lu}\p{Ll}
Yahoo![\s\u00A0]
\p{Ll}
\w['’][nNtT]\.[\s\u00A0]
\.\[\d+\][\s\u00A0]
\b[A-ZÀÉÈÍÓÒÚ]\.[\s\u00A0]
\b(dc|(?iu)(n|Mr|C|Dr|Dra|Dra\. Ma|Sta\. Ma|E|Emm|Emma|Excm|Excma|Hble|I|Il·lm|Il·lma|Il·ltre|Im|Ima|Mgfc|Mgfca|Mn|R|Rev|Sr|Sra|Sres|Srs|St|Sta|a|abr|abs|acad|add|adj|adm|admdor|admdora|admtiu|admtiva|adv|ag|agl|agr|agron|agròn|aj|ajud|al|alim|amb|ampl|ant|ap|apmt|apnt|apr|aprox|apt|arm|arq|arqueol|arquit|assign|assoc|atm|aut|aux|av|b|batx|bda|bibl|bl|bnc|butll|bxs|c|calef|cartogr|cat|catedr|catol|cf|cia|cin|cint|circul|cit|climat|col|col·l|compt|cons|constr|cont|contr|conv|corp|corr|cpl|cpt|cró|ct|cte|ctra|cts|d|dept|derog|des|desp|dg|dip|disp|distr|div|dj|dl|doc|drec|ds|dt|dta|dte|dupl|dv|e|econ|ed|ef|entl|esc|esp|espf|esq|ex|exc|exp|exped|ext|f|fac|fca|febr|fig|figs|fra|gen|gov|gral|i|imp|impr|impt|inc|insp|inst|int|inv|j|jul|jur|jurispr|leg|llic|loc|ltda|làm|merc|mil·l|màx|mín|neg|nov|nre|núm|o|oct|op|p|pàg|pàgs|paq|par|pda|pg|pl|pobl|pol|ppda|ppt|pral|prev|prof|progr|prov|pta|ptes|ptge|pvt|pàg|quadr|quint|r|rbla|ref|reg|rev|secr|serv|sgt|sotsp|subsp|supl|supt|t|tel|telegr|tit|trad|trans|transcr|transf|trav|tripl|trv|tt|tèc|univ|urb|v|var|veg|venc|vid|vig|vocab|vs|x|àt|íd))\.[\s\u00A0]
\b(s|ca)\.[\s\u00A0]
[XIV]+\b
\b(min|m|ca)\.[\s\u00A0]
[0-9]+\b
\b([Cc]ap|[Aa]rts?|pp|[Vv]ol)\.[\s\u00A0]
[XIV\d]+\b
\b(Ltd|[Ee]ds?|[Cc]oords?|\d+(r|n|t|è|é|a|rs|ns|es)|seg|masc|fem|sing|pl|adj|adv|g|kg|m|km|cm|ha|u|h|hrs|s|ss|alt|cant|cast|cert|com|dir|grs?|nom|parc|pres|set|Sr|Jr|Admón|Adm|Inc|Co|Hnos|Vda|[VU]d[s]?)\.[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]
[\-¡¿«»"'\u2018\u201C\p{Ps}\u2012\u2013\u2014\u2015\u2053]*\p{Ll}
\b(\p{L}\.)+[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]
\p{Ll}
\b([\p{Lu}]{2}\.)+[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]
\p{Ll}
\b\p{Lu}{2}\.[\s\u00A0]?
\p{Lu}{2}
EE\.[\s\u00A0]?UU\.[\s\u00A0]?
\p{Ll}
\b([Ee]tc|m[aáà]x|m[ií]n|aprox|\d+o)\.[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]
\p{Ll}
\bet al\.[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]
\b([Pp]ta[s]?|K[gm][s]|[mc]?[gmls]|[Hh](rs)?)\.[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]
\p{Ll}
[^\s\u00A0](\Q...\E|…)[\s\u00A0]
\p{Ll}
\b(\Q...\E|…)[\p{Pe}»"’”][\s\u00A0]
\p{Ll}
[\.…][\u00BB\u2019\u201D\u203A"'\u0002]*[\s\u00A0]
\b[\p{L}'’·\-]+[\p{Pf}\p{Pe}\u00BB\u2019\u201D\u203A"'\u0002]*[\.:!?…]+[\s\u00A0]
[¡¿«»"'\u2018\u201C"\p{Ps}]*\p{Lu}\p{L}*
[\.:!?…»]+[\s\u00A0]
»[^\u00A0\s\.:!?…]
¿[^?]+:[\s\u00A0]
.
Yahoo![\s\u00A0]
\p{Ll}
40dB.[\s\u00A0]
\p{Ll}
\.\[\d+\][\s\u00A0]
\b[A-ZÀÉÈÍÓÒÚ]\.[\s\u00A0]
[^\s\u00A0](\Q...\E|…)[\s\u00A0]
\p{Ll}
\b(\Q...\E|…)[\p{Pe}»"’”][\s\u00A0]
\p{Ll}
\b(s|ca)\.[\s\u00A0]
[XIV]+\b
\b(min|m|ca)\.[\s\u00A0]
[0-9]+\b
\b([Cc]ap|[Aa]rts?|pp|[Vv]ol|p|[Pp][aá]gs?|ps)\.[\s\u00A0]
[XIV\d]+\b
\b(\d+(r|er|n|ero|era|mo|ma|vo|va|no|na|to|ta|do|da|h|hr|gr|grs|o|a)s?|g|kg|m|km|cm|ha|u|h|hrs|H|HR|HRS|s|ss|alt|cant|cast|cert|com|dir|gr|nom|parc|pres|set|Sr|Jr|Admón|Adm|Inc|Co|Hnos|Vda|[VU]d[s]?)\.[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]
[\-¡¿«»"'\u2018\u201C\p{Ps}\u2012\u2013\u2014\u2015\u2053]*\p{Ll}
\b(https?|ftp|file|chrome|chromium|android|(chrome|moz)\-extension):///?[A-Za-z0-9\-]+\.
[A-Za-z0-9\-]+(\.|\b)
\b[A-Za-z0-9\-]+\.
[A-Za-z0-9\-]+\.(com|net|org|info|de|es|edu|co|eu|nl|io|cn|uk|gov|biz|ca|tk|ru|br|jp|pl)(\.|\b)
\b((?iu)(en|febr|mzo|abr|my|jun|jul|ag|agt|set|sept|setbre|oct|nov|novbre|dic|dicbre))\.[\s\u00A0]
\b(dc|(?iu)(n|[Aa]yto|Mr|C|Dr|Dra|E|Emm|Emma|Excm|Excma|Hble|I|Il·lm|Il·lma|Il·ltre|Im|Ima|Mgfc|Mgfca|Mn|R|Rev|Sr|Sra|Sres|Sras|Srs|St|Sta|a|abr|abs|acad|add|adj|adm|admdor|admdora|admtiu|admtiva|adv|ag|agl|agr|agron|agròn|aj|ajud|al|alim|amb|ampl|ant|ap|apmt|apnt|apr|aprox|apt|arm|arq|arqueol|arquit|assign|assoc|atm|aut|aux|av|b|batx|bda|bibl|bl|bnc|butll|bxs|c|calef|cartogr|cat|catedr|catol|cf|cia|cin|cint|circul|cit|climat|col|col·l|compt|cons|constr|cont|contr|conv|corp|corr|cpl|cpt|cró|ct|cte|ctra|cts|d|dept|derog|des|desp|dg|dip|disp|distr|div|dj|dl|doc|drec|ds|dt|dta|dte|dupl|dv|e|econ|ed|ef|entl|esc|esp|espf|esq|ex|exc|exp|exped|ext|f|fac|fca|febr|fig|figs|fra|gen|gov|gral|i|imp|impr|impt|inc|insp|inst|int|inv|j|jul|jur|jurispr|leg|llic|loc|ltda|làm|merc|mil·l|màx|mín|neg|nov|nre|núm|o|oct|op|p|pàg|pàgs|paq|par|pda|pg|pl|pobl|pol|ppda|ppt|pral|prev|prof|progr|prov|pta|ptes|ptge|pvt|pàg|quadr|quint|r|rbla|ref|reg|rev|secr|serv|sgt|sotsp|subsp|supl|supt|t|tel|telegr|tit|trad|trans|transcr|transf|trav|tripl|trv|tt|tèc|univ|urb|v|var|veg|venc|vid|vig|vocab|vs|x|àt|íd))\.[\s\u00A0]
\b([Aa]vda|[Pp][ol]|Pl?za|[Aa]dm|[Dd]pto|Sr|Mr|Srta|ej)\.[\s\u00A0]
\b(Dña|Dr[a]?|Sra|Sto|S(ri)?ta|Ldo|Ing|Prof|Excmo|Ilmo|Mgfco|admdor|admdora)\.[\s\u00A0]
\b([Aa]rt|[Cc]ód|[Ss]ecc|[Tt]ít)\.[\s\u00A0]
\b([Ee]d(it)?|[Nn]o|n|[Nn]úm|[Pp]ág|p|c|\d+er)|[V\.]gr\.[\s\u00A0]
\b(Ltd|[Ee]ds?|[Cc]oords?|\d+(r|n|t|è|é|a|rs|ns|es)|seg|masc|fem|sing|pl|adj|adv|g|kg|m|km|cm|ha|u|h|hrs|s|ss|alt|cant|cast|cert|com|dir|grs?|nom|parc|pres|set|Sr|Jr|Admón|Adm|Inc|Co|Hnos|Vda|[VU]d[s]?)\.[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]
[\-¡¿«»"'\u2018\u201C\p{Ps}\u2012\u2013\u2014\u2015\u2053]*\p{Ll}
\b(\p{L}\.)+[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]
\p{Ll}
\b([\p{Lu}]{2}\.)+[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]
\p{Ll}
\b\p{Lu}{2}\.[\s\u00A0]?
\p{Lu}{2}
EE\.[\s\u00A0]?UU\.[\s\u00A0]?
\p{Ll}
\b([Ee]tc|m[aá]x|m[ií]n|aprox|\d+o)\.[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]
\p{Ll}
\bet al\.[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]
\b([Pp]ta[s]?|K[gm][s]|[mc]?[gmls]|[Hh](rs)?)\.[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]
\p{Ll}
[\.…][\u00BB\u2019\u201D\u203A"'\u0002]*[\s\u00A0]
\b[\p{L}'’·\-]+[\p{Pf}\p{Pe}\u00BB\u2019\u201D\u203A"'\u0002]*[\.:!?…]+[\s\u00A0]
[¡¿«»"'\u2018\u201C"\p{Ps}]*\p{Lu}\p{L}*
[\.:!?…»]+[\s\u00A0]
»[^\u00A0\s\.:!?…]
\b(https?|ftp|file|chrome|chromium|android|(chrome|moz)\-extension):///?[A-Za-z0-9\-]+\.
[A-Za-z0-9\-]+(\.|\b)
\b[A-Za-z0-9\-]+\.
[A-Za-z0-9\-]+\.(com|net|org|info|de|es|edu|co|eu|nl|io|cn|uk|gov|biz|ca|tk|ru|br|jp|pl)(\.|\b)
\r?\n[\u00A0\s]*[-*]+[\u00A0\s]
\d+[a-z]\.[\u00A0\s]{1,2}
\p{Lu}
[^-\p{L}'’/°]\p{L}[\.!?…]['|"|“|«|\)|\]|\}]?[\u00A0\s]
([Dd](as|er|ie|iese[rsmn]?|en|em)|[kmsd]?ein(e[rsnm]?)?|am|fürs|ins|zum|im|am|zur) \d+\.[\u00A0\s]+
[A-ZÄÖÜ].*
Ust.
Id
Prof.
Dr
Dr.
iur|med|oec|phil|rer|theol
(?i)FRITZ!
(?i)Box
ID.
3|4|Buzz|Crozz
[1-3]\.[\u00A0\s]{1,2}
Liga|Bundesliga|(Fußball|Handball|Basketball)(-B|b)undesliga
\d+\.[\u00A0\s]{1,2}
Klässler[sn]?
\bP[Hh]\.
D\.
\b\p{L}\.
[\u00A0\s]\p{L}\.[\u00A0\s]{1,2}
\p{L}\.
[\[\(]?\.\.\.[\]\)]?[\u00A0\s]{1,2}
\p{Ll}
['"„][\.!?…]['"“«»][\u00A0\s]{1,2}
["'“«»][\u00A0\s]{1,2}
\p{Ll}
[\u00A0\s]([\.!?]{1,3}|…)['|"|“|«|\)|\]|\}]?[\u00A0\s]{1,2}
\b\d+\.[\u00A0\s]{1,2}
\p{Ll}|\p{Lu}{2,}
[\(\[][!?]{1,3}[\]\)][\u00A0\s]{1,2}
[!?]{1,3}[\)\]][\u00A0\s]{1,2}
[\(\)\[\]][\u00A0\s]
[\u00A0\s ][IVX]+\.[\u00A0\s]{1,2}
[^\p{Lu}]+
\d+\.[\u00A0\s]{1,2}
(und|oder|bis)[\u00A0\s]
\d+\.[\u00A0\s]{1,2}
Januar|Jänner|Februar|März|Merz|April|Mai|Ju[ln]i|August|September|Oktober|November|Dezember
\d+\.[\u00A0\s]{1,2}
J[aä]n|Febr?|Mär|Apr|Mai|Ju[nl]|Aug|Sept?|Okt|Nov|Dez
(Jan|Jän|Febr?|Mär|Apr|Mai|Ju[nl]|Aug|Sept?|Okt|Nov|Dez)\.[\u00A0\s]{1,2}
\d\d(\d\d)?
\d+\.[\u00A0\s]{1,2}
Amtsperiode|Breitengrads?|Breitengrades|Jubiläum|Jhd?|Jhdts?|Konferenz|(Jahres|Partei)(-K|k)onferenz|Längengrade?s?|Tags?|Tages|(Jahres|Spiel|Partei|Geburts)tag|(Jahres|Spiel|Partei|Geburts)tages|(Jahres|Spiel|Partei|Geburts)tags|Jahrhunderts?|Jahrtausend|Platz|Platzes|Lebensjahrs?|Lebensjahres|Lochs?|Loches|Grads|Grades|Obergeschoss|Stock(werk)?s?|Etage|Klasse|Runde|Bezirk|Etappe|Staffel|Sinfonie
\b(Mrs?|No|pp|St|no|Sr|Jr|[Ss]ek|Bros|etc|[Bb]tw|vs|esp|[Ff]ig|Jan|Feb|Mar|Apr|Ju[nl]|Aug|Sept?|O[ck]t|Nov|Dec|PhD|BSc|BEng|BComp|BArch|al|cf|Inc|Ms|MEng|MSc|MComp|Gen|Sen|Prof|Corp|Co|co|Ltd|Buchst)\.[\u00A0\s]{1,2}
\b(spp?)\.[\u00A0\s]{1,2}
\b(betr|Geb|Stk|ggü|Mag|mtl|Flgh?|[Pp]arl|Bsp|versch|[Dd]iesbzgl|[Zz]ykl|[Dd]bzgl[Ss]tellv|d|Übers|usw|[Bb]zw|Ab[hkst]|[Ee]ig|[Aa]bzü?gl|\d+-tlg|tlg|[Gg]gfls|[Ff]achspr|[Ll]tda|[Ee]inschl|[Vv]mtl|[Ss]tellv|Ev|[Bb]ezgl|lit|Abzw|[Vv]sl|ahd|Akk|aktual|[Öö]ffentl|prof|allg|alltagsspr|altdt|alttest|amerikan|Anh|Ank|Anm|Art|[Aa]utom|Auftragsnr|Az|Bat|bayr|Bde?|bearb|Bed|Bem|bes|bez|wsl|vsl|Bez|Bhf|Blvd|[Bb]spw|btto|bw|Dtl|[Gg]esetzl|Dez|[Jj]gdfr|[Ee]ff)\.[\u00A0\s]{1,2}
\b(cts?|[Cc]a|chem|chin|Chr|cresc|[Dd]at|desgl|ders|dgl|Dipl|Dir?|Doz?|durchg|durchges|Dr|[Dd]t|ebd|Ed|[Ee]igt?l|akt|[Ee]ngl|Erg|al|et[cw]|Etw|ev|[Ee]vtl?|[Ee]xkl|Expl|Exz)\.[\u00A0\s]{1,2}
\bDipl\.-[A-Z][a-z]{2,4}\.[\u00A0\s]{1,2}
\b[BM]\.[\u00A0\s]Sc\.[\u00A0\s]
\p{Ll}
\b(ff|Fa|fachspr|fam|fem|Fem|Fr|franz|[Ff]rz?|[Aa]ltfranz|frdl|Frl|Fut|Gd|gebr?|Gebr|geh|geleg|gen|Gen|germ|gesch|ges|get|ggf|Ggf|Ggs|ggT|Gr|[Gg]rds|griech)\.[\u00A0\s]{1,2}
\b(hebr|hg|hl|Hrsg|Hg|hist|hochd|hochspr|Hptst|Hr|hrsg|Allg|IdNr|ill|[Ii]nkl|[Ii]ncl|[Ee]hem|Ind|Inf|Ing|ital|Tr|jap|Jb|Jg|Jhd?|Jhdts?|jmd[mns]?|jur|Kap|kart|kath|kfm|kaufm|Kfm|kgl|Kl|Konj|königl|Krs?|Kto)\.[\u00A0\s]{1,2}
\b([A-ZÖÄÜ][a-zöäüß]+nr|tel|[Gg]em|Pat|prov|Betr|lat|lfd|Lit|lt|Lz|Mask|mask|max|Mrd|mdal|me[dt]|phil|mhd|Mio?|mio|mind?|Mo|mod|nachm|nördlBr|neutr|Nhd|Nom|Nrn?|Num|Obj|od|dgl|offz)\.[\u00A0\s]{1,2}
\b(Part|Per[fs]|Pfd|Pl(ur)?|pl|Plusq|Pos|pp|Prä[ps]|Prät|Pro[vf]|rd|reg|resp|Rhld|rit|Sa|südl|Br|se[ln]|Sept|Sing|sign|So|sog|Sp|[Ss]td?|stacc|Str|stud|Subst|sva|svw|sZ)\.[\u00A0\s]{1,2}
([A-ZÖÄÜ][a-zöäüß]+str)\.[\u00A0\s]{1,2}
\p{Ll}
\d+\.\d+\.[\u00A0\s]
[\-–][\u00A0\s]\d+
\b(Tel|teilw|Temp|trans|Tsd|übertr|übl|ff|überarb|ugs|univ|unveränd|urspr|USt|UST|USt\-IdNr|[Aa][bn]schl|sw|kl|[Gg]r|vgl|vll|Vll|vlt|Vlt|vllt|Vllt|Vgl|Vol|vollst|vorm|Vp|Vs|vs|wesentl|voraussichtl|[Rr]echts?staatl|[Ss]taatl|wg|Whg|Hd|Ztr|zus|Zus|zzt?|zzgl|zB|zb|Zz|Zt|zw|Min|Bzgl|bzgl|bezügl|Frhr|ggfs|insb|autom|Mw[sS]t)\.[\u00A0\s]{1,2}
[\.!?…][\u0002|'|"|“|«|‹|\)|\]|\}¹²³]?[\u00A0\s]+
[\.!?…]['"“\p{Pe}\u00BB\u201D]?
\p{Lu}[^\p{Lu}]
[\u00A0\s]\p{L}[\.!?…][\u00A0\s]{1,2}
\p{Lu}\p{Ll}
[\.!?][”“]
[“„]
'\p{L}[\.!?…]\s
\p{Lu}
\sno[\.!?…]\s
\p{Lu}
[ap]\.m\.\s
\p{Lu}
[^-\p{L}]\p{L}[\.!?…]['|"|«|\)|\]|\}]?\s
\b\p{L}\.
\s\p{L}\.\s
\p{L}\.
[\[\(]?\.\.\.[\]\)]?\s
\p{Ll}
['"][\.!?…]['"]\s
["']\s
\p{Ll}
\b\d+\.\s
\p{Ll}|\p{Lu}{2,}
[\(\[][!?]{1,3}[\]\)]\s
[!?]{1,3}[\)\]]\s
[\(\)\[\]]\s
\d+\.\s
(og|eller|til)\s
\b\p{N}+\.\s
januar|februar|marts|april|maj|ju[ln]i|august|september|oktober|november|december
\d+\.\s
januar|februar|marts|april|maj|ju[ln]i|august|september|oktober|november|december
\b(Mrs?|No|pp|St|no|Sr|Jr|Bros|vs|esp|[Ff]ig|Jan|Feb|Mar|Apr|Ju[nl]|Aug|Sep|Sept|Oct|Okt|Nov|Dec|PhD|al|cf|Inc|Ms|Gen|Sen|Prof|Corp|Co)\.\s
\bP[Hh]\.\s?
D\.?
\b[BM]\.\s?
Eng\.?
\bLL\.\s?
[BMD]\.?
\b[BM]\.\s?
Sc\.?
\b[BM]\.\s?
Comp?\.?
\b[BM]\.\s?
Arch\.?
\b(abs|abstr|adj|adm|adr|adv|afd|afg|afl|afs|afvig|agro|akad|akk|allr|alm|amer|anat|ang|anm|anv|apot|appos|apr|arab|arb|arkais|arkæol|arp|arr|art|ass|astr|att|attrib|aud|aug|aut)\.\s
\b(bag|barb|barnespr|bd|bdt|beg|besl|best|bet|bhk|biavl|bibet|bibl|bibliot|billard|billedl|biol|bjergv|bk|bl|bogb|bogh|bogtr|bornh|bot|br|bryg|bto|bygn|bødk)\.\s
\b(ca|cand|Chr|cirk|cit|co|d|da|dagl|dans|dat|dec|def|demonstr|dep|dial|diam|dim|dipl|disp|distr|distrib|dobb|dok|dr|dvs|e|egl|ejd|eks|eksam|ekskl|eksp|ekspl|el|ell|ellipt|emb|endv|eng|enk|ent|etnogr|eufem|eur|event|evt)\.\s
\b(f|fagl|fakt|farv|feb|ff|fhv|fig|filos|fin|fisk|fk|fl|flg|flt|flyv|fmd|fon|foragt|forb|foreg|forf|forsikr|fors|forsk|forst|forv|foræld|fot|fr|fre|fris|frk|fsv|fuldm|fx|fys|fysiol|fægt|gart|gartn|garv|gdr|gen|genopt|geogr|geol|geom|germ|gl|glarm|glda|gldgs|glholl|glno|gns|got|gr|gradbøjn|graf|gram|gross|grundbet|græc|guldsm|gym)\.\s
\b(hat|hd?|hebr|henh|hensobj|herald|hhv|hist|hj|holl|hovedbet|hr|hty|højtid|haandarb|haandv|if?|iflg|ifm|ift|iht|imp|incl|indb|indik|inf|ing|Inkl|inkl|insp|instr|interj|intk|intr|iron|isl|ital|jan|jarg|jernb|jf|jnr|jr|jul|jun|jur|jy|jæg|jærnb|jød)\.\s
\b(Kbh|kbh|kem|kgl|kirk|kl|kld|knsp|kog|koll|komm|komp|konj|konkr|kons|Kr|kr|kurv|kvt|køkkenspr|l|landbr|landmaaling|lat|lb|lic|lign|litt|Ll|log|Loll|loll|lrs|lør)\.\s
\b(m|maj|maks|mal|man|mar|mark|mat|mdl|mdr|med|medl|meng|merc|meteorol|meton|metr|mf|mfl|mht|mia|mil|min|mineral|mio|ml|mlat|mm|mnt|mods|modsætn|modt|mr|mrk|mur|mvh|mytol|møl|mønt|n|naturv|ndf|Ndr|nedsæt|nht|no|nom|nov|nr|nt|num|nyda|nydann|nylat|naal)\.\s
\b(obj|obl|oblik|obs|odont|oecon|oeng|ofl|ogs|oht|okt|oldfr|oldfris|oldn|olgn|omg|omkr|omtr|ons|opr|ordspr|org|osax|ovenst|overf|overs|ovf|p|pag|parl|part|pass|pat|pct|perf|pers|pga|ph|pharm|phil|pk|pkt|pl|plur|poet|pol|polit|pop|port|poss|post|pott|pr|prod|pron|propr|prov|præd|præp|præs|præt|psych|pt|pæd|paavirkn)\.\s
\b(reb|ref|refl|regn|rekl|relat|relig|resp|retor|rev|rid|rigsspr|run|russ|s|sa|sanskr|scient|sdjy|sdr|sek|sen|sep|sept|shetl|sj|sjæll|skibsbygn|sko|skol|skr|skriftspr|skræd|Skt|slagt|slutn|smed|sml|smsat|smst|snedk|soc|soldat|sp|spec|sport|spot|spr|sprogv|spøg|ssg|ssgr|st|stat|stk|str|straf|stud|subj|subst|superl|sv|sætn|søfors|søn)\.\s
\b(talem|talespr|tandl|td|tdl|teat|techn|telef|telegr|telekom|teol|th|theol|tir|tirs|tlf|told|tor|tors|trans|tsk|ty|tyrk|tøm|u|ubesl|ubest|udd|uddan|udenl|udg|udtr|uegl|ugtl|ult|underbet|undt|univ|upers|ur|urnord)\.\s
\b(vs?|var|varem|vbs|vedk|vedl|vedr|vejl|verb|vet|vha|vol|vsa|vulg|væv|zool|æ|æda|ænht|ænyd|æstet|ø|økon|å|årg|årh)\.\s
\b(etc|mv|osv)\.\s
\p{Ll}
[\.!?…][\u0002|'|"|«|\)|\]|\}¹²³]?\s+
[\.!?…]['"\p{Pe}\u00BB\u201D]?
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?…]\s
\p{Lu}\p{Ll}
\b(div|[Ee]kz|h|[Ii]nkl|p|[Rr]ed|[Rr]im|ktp)\.\s
\p{Ll}
\b([Bb]v|[Ĉĉ]|i\.a|k\.[acs]|[Tt]\.[ne]|k\.t\.p|n\.b|P\.S)\.\s
\b[Ll]ernu!\s
\p{Ll}
[\.!?…][\u0002|'|"|«|\)|\]|\}¹²³]?\s+
[\.!?…]['"\p{Pe}\u00BB\u201D]?
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?…]\s
\p{Lu}\p{Ll}
[\s\u00A0]
[»”’"'›]
ambass|cuil|p|liv|assoc|bibl|ENREG|al|phot|circ|concl|deb|dest|dupl|éd|écon|incl?|ital|jur|juris|jurispr|larg|lex|législ|longit|(?-i)RR|(?-i)ÉÉm|(?-i)EExc|métr|méd|néol|obs|plur|préf|prog|publ|trib|trim|suiv|(?-i)LL|env|élem|ér|ét|hon|hypexp|conj|coop|ch|alph|anglic|app|pr|collab|paragr|sect|para|commiss|coord|dép|dir|gér|secour|sén|gén|abrév|adj|adr|anon|append|av|auj|bibl|bibliogr|bdc|boul|bull|bur|caar|cat|cell|chap|cir|compl|cf|corres|dest|dict|div|dom|dr|édif|éd|électr|élém|encycl|fig|fl|graph|hist|hyp|ill|imm|imp|impr|incl|inc|ind|in[gtvf]|jur|lat|litt|liq|loc|liv|livr|méd|mém|pl|réd|rel|sc|suiv|sup|suppl|trad|univ|mus|pharm|soc|pol|compt|urb|act|confect|exp|réal|prov|introd|inv|tial|enr|ép|équiv|esp|étym|excl|exc|ap|arr|arch|adv|al|anc|angl|ann|gest|gouv|prés|rect|représ|resp|scrut|vol|coll|réf|id|sqq?|janv|fév|avr|juill|oct|nov|déc|admin
\p{Ll}.*
\p{Ll}.*
ambass|cuil|p|liv|assoc|bibl|oct|déc|jan|fév|avr|juil|sept|nov|ENREG|al|circ|concl|deb|dest|dupl|éd|écon|incl?|ital|jur|juris|jurispr|larg|lex|législ|longit|(?-i)RR|(?-i)ÉÉm|(?-i)EExc|métr|méd|néol|obs|plur|préf|prog|publ|trib|trim|suiv|(?-i)LL|env|élem|ér|ét|hon|hypexp|conj|coop|ch|alph|anglic|app|pr|collab|paragr|sect|para|commiss|coord|dép|dir|gér|secour|sén|gén|abrév|adj|adr|anon|append|av|auj|bibl|bibliogr|bdc|boul|bull|bur|caar|cat|cell|chap|cir|compl|cf|corres|dest|dict|div|dom|dr|édif|éd|électr|élém|encycl|fig|fl|graph|hist|hyp|ill|imm|imp|impr|incl|inc|ind|in[gtvf]|jur|lat|litt|liq|loc|liv|livr|méd|mém|pl|réd|rel|sc|suiv|sup|suppl|trad|univ|mus|pharm|soc|pol|compt|urb|act|confect|exp|réal|prov|introd|inv|tial|enr|ép|équiv|esp|étym|excl|exc|ap|arr|arch|adv|al|anc|angl|ann|gest|gouv|prés|rect|représ|resp|scrut|vol|coll|réf|id|sqq?|janv|fév|avr|juill|oct|nov|déc|admin
.*°C
de
[\.!?][\s\u00A0][»”’"'›][\s\u00A0]
[«“‘‹"'\p{Lu}]
Yahoo![\s\u00A0]
\p{Ll}
(\!|\?)[\s\u00A0]
\p{Ll}
\.\[\d+\][\s\u00A0]
\b(https?|ftp|file|chrome|chromium|android|(chrome|moz)\-extension):///?[A-Za-z0-9\-]+\.
[A-Za-z0-9\-]+(\.|\b)
\b[A-Za-z0-9\-]+\.
[A-Za-z0-9\-]+\.(fr|com|net|org|info|de|es|edu|co|eu|nl|io|cn|uk|gov|biz|ca|tk|ru|br|jp|pl)(\.|\b)
\b[A-Za-z0-9\-]+\.
[A-Za-z]{2,5}(\.|\b)
\b((?iu)J\.\-C|art|app|cf|chap|e(nv|tc)|fém|fig|masc|p|sing|suiv|suppl|tél|op|ex)\.[\s\u00A0]
\p{Ll}
\b(etc)\.\)[\s\u00A0]
\b(apr|ave?|boul|Mr?|Mrs|MM?|Mlle)\.[\s\u00A0]
[\[\(]*…[\]\)]*
\p{Ll}
\p{Ps}[!?]+\p{Pe}
[\.!?…]+\p{Pe}
\p{Ll}
["”'’][\s\u00A0]*
[\s\u00A0]*\p{Ll}
['"„][\.!?…]['"”][\s\u00A0]
\b\p{L}\.[\s\u00A0]
\p{L}\.[\s\u00A0]
\b\p{L}\.
\p{L}\.
(…|\.\.\.)[\s\u00A0]?\)[\s\u00A0]
[^\p{P}]
(…|\.\.\.)[\s\u00A0]?\?\)[\s\u00A0]
[^\p{P}]
\p{Lu}\p{L}+[\s\u00A0]v\.[\s\u00A0]
\p{Lu}\p{L}+
[^,][\s\u00A0]\p{L}{2}\.[\s\u00A0]
\p{N}+\)[\s\u00A0]
[\.\s\u00A0]\p{L}{1,2}\.[\s\u00A0]
[\p{N}\p{Ll}]
[\[\(]*\.\.\.[\]\)]*
[^\p{Lu}]
\b\p{Lu}\.[\s\u00A0]\p{Lu}\.[\s\u00A0]
\b\p{Lu}\.\p{Lu}\.[\s\u00A0]
[^\.][\s\u00A0][A-Z]\.[\s\u00A0]
\b(:?Blvd|Ave|Mts?)\.[\s\u00A0]
\p{Ll}+
\b(?:Kan|Ill|M[ai]ss)\.[\s\u00A0]
\p{Ll}+
\(\p{Ll}+\.[\s\u00A0]
i\.e\.[\s\u00A0]
[A-Z]\.[A-Z]\.
[A-Z]\b
\bL\.
A\b
\bU\.
[SK]\b
\b[nN]o\.[\s\u00A0]
\p{N}
\bP[Hh]\.[\s\u00A0]?
D\.?
\be\.g\.[\s\u00A0]
\bvs\.[\s\u00A0]
\b[Ee]tc\.[\s\u00A0]
[^\p{Lu}]
\b([Bb]tw|BTW)\.[\s\u00A0]
(?i)FRITZ!
(?i)Box
ID.
3|4|Buzz|Crozz
\bP[Hh]\.?[\s\u00A0]?[Dd]\.[\s\u00A0]
\b(P[hH][dD]|BSc|BEng|BComp|BArch|MSc|MEng|MComp)\.[\s\u00A0]
\bLL\.[\s\u00A0]?[BMD]\.[\s\u00A0]
\b[BM]\.[\s\u00A0]?
Eng\.?
\bLL\.[\s\u00A0]?
[BMD]\.?
\b[BM]\.[\s\u00A0]?
Sc\.?
\b[BM]\.[\s\u00A0]?
Comp?\.?
\b[BM]\.[\s\u00A0]?
Arch\.?
\b[BM]\.?[\s\u00A0]?(Sc|Eng|Comp|Arch)\.[\s\u00A0]
\bI(nc|NC)\.[\s\u00A0]
\bCorp\.[\s\u00A0]
\bBros\.[\s\u00A0]
\bLtd\.[\s\u00A0]
\p{Ll}+
\bCo\.[\s\u00A0]
\bE\.[\s\u00A0]
\b[Cc]oli\b
[\.!?…][\u0002|'|"|«|\)|\]|\}¹²³]?[\s\u00A0]+
[\.!?…]['"\p{Pe}\u00BB\u201D]?
\p{Lu}[^\p{Lu}]
[\s\u00A0]\p{L}[\.!?…][\s\u00A0]
\p{Lu}\p{Ll}
\b[0-9]+(\.|:)[0-9][0-9][\s\u00A0\u202F]
(^|[\h])(\.\.\.|…)
\p{Lu}
\b(в|у|на|за|з|із|зі|зо)(\.\.\.|…)[\h\v]*
\p{Lu}
[.!?…][»“]?[\h]+
[\h]*([«"„“(]|[‐-―-][\h])\p{Ll}
\v[\h]*
(\.\.\.|…)
\b\d{1,3}\.[\h]+
\p{Ll}|\p{Lu}{2,}
\b\p{Ll}+[.!?][\h\v]*
\h*(([\(«]|[\[‐-―-][\h\v]*)?\p{Ll})
([\[\(]*[\]\)]*|\.\.\.|…)[\h\v]+
[\h\v]*\p{Ll}
\b\p{L}{1,2}\.
\p{L}{1,2}\.
\b[\u00A0\u202F]?[A-Z]\.[\h\v]?
[A-Z][a-zA-Z'’.-]|[А-ЯІЇЄҐ]\.
(^[\h\v]*|\([\h\v]*|[«„"]|(\b[А-ЯІЇЄҐACEIHOPX]\.-))[А-ЯІЇЄҐA-Z]\.[\h\v]*
[\h\v][А-ЯІЇЄҐ]\.[\h\v]*
[А-ЯІЇЄҐ]\.|[0-9]|[\h\v]*,|[\h\v]*[:«]|\([0-9]{4}
[\h\v.]([А-ЯІЇЄҐACEIHOPX]\.-)?(?<!°)[А-ЯІЇЄҐABCEIHOPX](?<!(Куан[\h]+Ю|(Петр|Олександр)([аоу]|ові|ом)?[\h]+[IІ]+))\.[\h\v]*
[А-ЯІЇЄҐ][а-яіїєґА-ЯІЇЄҐ'’ʼ]{3}
(^|[\h\v])(Ів|Дж)\.[\h\v]+
[А-ЯІЇЄҐA-Z]
\b([0-9]{2}|[0-9]{4})[\h\v]+р\.[\h\v]+
[\h\v]*[№0-9‐-―-]
(?<!\d[\h]*)\bр\.[\h\v]*
[\h]*(?!(На|Але|Так?)[\h\v]+)[А-ЯІЇЄҐA-Z][^\h]
[А-ЯІЇЄҐ][а-яіїєґ'’-]*([\h]+[а-яіїєґ'’-]+)?[\h](\d{4}[‐-―-])*\d{4}[\h]*р\.[\h\v]*
[\v\h]*(?!(На|Але|Так?)[\h\v]+)[А-ЯІЇЄҐA-Z][^\h\v]
\d{1,2}[\h]+[а-яіїєґ]+[\h]\d{4}[\h]*р\.[\h\v]*
[\h]*(?!(На|Але|Так?)[\h\v]+)[А-ЯІЇЄҐA-Z][^\h\v]
\b([0-9]0|[0-9]{3}0)(-[мх])?рр\.[\h\v]*
\b(тис|млн|млрд|грн)\.[\h\v]*
[\h\v]*(\d|[КМ]Вт)
\b(укр|рос|англ?|амер|італ|ісп|нім|фр(анц)?|лат|грец(ьк)?)\.[\h\v]*
\b(абз|арк|ауд|бл|буд|бульв|вул|держ|дод|зав|зб|зв|зовн|екон|к|кв|канд|кн|напр|нпр|нац|обл|оп|пл|пол|поч|пп|пор|просп|розд|стор|табл|[Тт]]ел|ч|част)\.[\h\v]*
\b(кін)\.[\h\v]*
[а-яіїєґ0-9IXV]|[ІХ]+\b
\b[сС]т\.[\h\v]
[\h]*(?!([АВУОІЄ]|На|Але|Так?)[\h\v])
([0-9]|[-–—])[\h\v]+нар\.[\h\v]*
\bнар\.[\h\v]*
([0-9]|бл\.|арт\.)
\bдол\.[\h\v]*
США
(?<!т\.[\h\v]?)\b[пд]\.[\h\v]*
\b(див)\.[\h\v]
[\h\v]*[^А-ЯІЇЄҐ]
[,‐-―-][\h\v]*(див)\.[\h\v]*
(\([^)]*|\[[^\]]*|,[\h\v]*)\b(див)\.[\h\v]*
\b(ап|[Аа]кад|[Пп]роф|[Дд]оц|[Аа]сист|[Рр]еж|[Аа]рх|[Сс]вв?|о|оз|ім|інж|дир|тов|упоряд|тт|чл\.-кор|[Пп]реп)\.[\h\v]*
[\h\v]*[А-ЯІЇЄҐA-Z]
(?<![іи]\s+)\bдр\.[\h\v]*
[\h\v]*[А-ЯІЇЄҐ]
\bМан\.[\h\v]*
[\h\v]*([Сс]іті|[Юю]н)
[^0-9][\h\v]+[Гг]р\.[\h\v]*
[\h\v]*[А-ЯІЇЄҐA-Z]
\b([Аа]рт|[Мм]ал|[Рр]ис)\.[\h\v]*
[\h\v]*[0-9]
[0-9][\h\v]+(арт|тт)\.[\h\v]*
(?<!\d[\h\v]*)\bм\.[\h\v]*
[А-ЯІЇЄҐ][а-яіїєґ']
([\h\v][«(][см]|[^0-9/. ][\h\v]+[см])\.[\h\v]+
[А-ЯІЇЄҐ][а-яіїєґ']
[(«"„“”\[‹][а-яіїєґ]+\.[\h\v]+
["«„“”\[][.!?…]{1,3}["»”“\]][\h\v]+
[\h\v]*[‐-―-][\h\v]*([Рр]ед|[Аа]вт)\.[\h\v]*[\)\]]
\b([Рр]ед)\.[\h\v]*
[А-ЯІЇЄҐ]
[а-яіїєґ]\.
НЕТ|Інфо|Info|City|Life|UA|Ру
(?<!\h[А-ЯІЇЄҐ])[.!?…]{1,3}\u202F[\h\v]+
[.!?…]['»"„“”\]›\u0002]*[\h\v]+
[.!?…]['»"„“”)\]›]*
\p{Lu}[^\p{Lu}]
[.!?…]['»"„“”)\]›]?[\h\v]+
([‐-―-][\h\v]*)?\p{Lu}[^\p{Lu}]
\b\d+\.\s
\p{Ll}|\p{Lu}{2,}
\b[А-ЯЁ]\.\s
\bЎ\.\s
\b[A-Z]\.\s
\b\p{L}\.
\p{L}\.
\b[0-9]+(г)\.\s
\b[XVILMC]+(ст)\.\s
\b[0-9]+(\.|:)[0-9][0-9]\s
\b[0-9]+(\.|:)[0-9][0-9](\.|:)[0-9][0-9]\s
\b[0-9]+(г|гг|грн|млн|млрд|руб|тыс)\.\s
\b(в|вв|г|гг|грн|млн|млрд|руб|ст|р|тыс)\.\s
['"„][\.!?…]['"”]\s
[\u00AB][\.!?…][\u00BB]\s
[\[\(]*\.\.\.[\]\)]*
\p{Ll}
[\[\(]*…[\]\)]*
\p{Ll}
["”'\u00BB]\s*
\s*\p{Ll}
[\.!?…]['"\u00BB\u2019\u201D\u203A\u0002¹²³]*\s
\u005D\u005D\s
[\.!?…]['»"”\p{Pe}]*
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?…]\s
\p{Lu}\p{Ll}
\bs([eé]c)?\.\s?
[IVXVDMCL]+
\b[Ee]tc\.[\p{Pe}\p{Pf}\p{Pd}"']*\s
\p{Ll}
\b(m[aá]x|m[ií]n|[aA]prox)\.[\p{Pe}\p{Pf}\p{Pd}"']*\s
[\p{Ll}\p{N}]
\b([aA]pt?do|[aA]sdo|[aA]vd?a?|[Cc]ód|[Dd]e?pto|[Ff]ac|[Ii]nst)\.\s
\b(S\.A\.[IRS]\.|S\.R\.M\.|A\.R\.|S\.[ME]\.)\s
\p{Lu}
\b([\p{Ll}\p{Lu}]\.)+[\p{Pe}\p{Pf}\p{Pd}"']*\s
\p{Ll}
\b\p{L}\.\s?
((\p{L}\.\s?)+|\p{Ll})
\b\p{Lu}{2}\.\s?
(\p{Lu}{2}\.?\s?|\p{Ll})
\b([Aa]fm[oa]s?|Emcia|Ilt?m[ao]s?|Iltres?|MM|Exc?m[ao]s?|Magf[oa]|D(na)?|Sra?|Sr[ea]s|Srta|Dra?|Dr[ea]s?|Rm[ao]|Rev|Revm[ao]|Mons|Emmo|Rv?d[ao]|[Ll]icd[oa]|[Ll]ic|[Ll]d[oa]|[pP]rofs?)\.\s
\b([Nn][úu]ms?|[fF]igs?|[Pp][aá]xs?|pp?|cc?a)\.\s
\p{N}
\b([Vv]ols?|[Cc]aps?)\.\s
\p{N}|[IVXVDMCL]+
\b([Aa]dmóns?|[aA]d(mt)?v[oa]s?)\.\s
\p{Ll}
\b([pP]pal|[Vv]des?|[Ii]b[íi]d|[Rr]efs?|[Cc]it|[Aa]brevs?|[Aa]bl|[Aa]dx|[Aa]dv|[Aa]cr|[Cc]onx|[Ll]oc|[Pp]rep|[Ss]ubst)\.\s
[^\p{Lu}]
\b([vV]id|[Cc]fr?)\.\s
\b([Cc]oord|[Ee]d)s?\.\s
\b([Cc]t[ae]|[Tt]e?lf|[Tt]fno|[Tt]el[eé]f|[Tt]el)s?\.\s
[^\p{Lu}]
\b([oO]p|[lL]oc)\.\s?
cit\.
\bet [aá]l\.\s?
[\p{Ll}\p{N}]
['"\(][\.!?…]['"\)]\s
\bvs\.\s
\besp\.\s
(…|\.\.\.)\s
\p{Ll}
[\.!?…]\s
[-–—],?\s\p{Ll}.+
[\.…][\u00BB\u2019\u201D\u203A"'\u0002]*\s
\s\p{L}+[\p{Pf}\p{Pe}\u00BB\u2019\u201D\u203A"'\u0002]*[\.:!?…]+\s*
[¡¿«»"'\p{Ps}]*\p{Lu}\p{L}*
[^\s]:\s
['"«¡¿\p{Ps}\p{Pi}]?\p{Lu}\p{Ll}*
[:]+[\p{Pe}\p{Pf}\p{Po}"-[\u002C\u003A\u003B\u055D\u060C\u061B\u0703\u0704\u0705\u0706\u0707\u0708\u0709\u07F8\u1363\u1364\u1365\u1366\u1802\u1804\u1808\u204F\u205D\u3001\uA60D\uFE10\uFE11\uFE13\uFE14\uFE50\uFE51\uFE54\uFE55\uFF0C\uFF1A\uFF1B\uFF64]]*
\s+\P{Lu}
[:]+[\p{Pe}\p{Pf}\p{Po}"-[\u002C\u003A\u003B\u055D\u060C\u061B\u0703\u0704\u0705\u0706\u0707\u0708\u0709\u07F8\u1363\u1364\u1365\u1366\u1802\u1804\u1808\u204F\u205D\u3001\uA60D\uFE10\uFE11\uFE13\uFE14\uFE50\uFE51\uFE54\uFE55\uFF0C\uFF1A\uFF1B\uFF64]]*
\s
[。．！？…]+
.
\.\.\.
\s+\P{Lu}
^\s*\p{Nd}+[\p{Nd}\.\)\]]+\s+
\p{Lu}
[\.\?\!]+
\s
[\.!?…][\u00BB\u2019\u201D\u203A"'\p{Pe}\u0002¹²³]*\s
\s\p{L}[\.!?…]\s
\p{Lu}\p{Ll}
\b[dD]\.l\.e\.?
[\.!?…]['"”»\p{Pe}\u00BB\u201D]?\s*
\p{Lu}[^\p{Lu}]
[\.!?…][\u0002|'|"|«|\)|\]|\}¹²³]?\s+
[\.!?…]['"\p{Pe}\u00BB\u201D]?
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?…]\s
\p{Lu}\p{Ll}
\b(https?|ftp|file|chrome|chromium|android|(chrome|moz)\-extension):///?[A-Za-z0-9\-]+\.
[A-Za-z0-9\-]+(\.|\b)
\b[A-Za-z0-9\-]+\.
[A-Za-z0-9\-]+\.(com|net|org|info|de|es|edu|co|eu|nl|io|cn|uk|gov|biz|ca|tk|ru|br|jp|pl)(\.|\b)
\b(a|Ab|abr|abrev|absol|acad|Açor|A\. ?D|add|adj|adv|advers|Aeron|afér|Agric|ago|Álg|aprox|[Aa]rts?|Artilh|auxil|av|Av)\.\s?
\b(Bot|barb|B\.el|Bibl|Biol|Bioquím|burl)\.\s?
\b(ca|card|cat|caus|cf|cit|cód|comp|compar|conj|contr|coord|cop)\.\s?
\b(D|def|dem|deprec|deriv|det|dez|disj|[Dd]ra?s?)\.\s?
\b(Ecol|Econ|ed|elem|Eng|erud|estrang|ex|Ex)\.\s?
\b(etc)\.\s?
\p{Ll}
\b(f|fam|Farm|fem|fev|fig|fin|fl|fr|frac)\.\s?
\b(gén|geog|Geogr|Geol|Geom|gír|gloss|Gram)\.\s?
\b(hab|hist|Hort)\.\s?
\b(Ibid|id|i.e|incompat|indef|inf|infant|Inform|integr|interj|interr|intr|inv)\.\s?
\b(jan|jul|jun|Jorn|Jur)\.\s?
\b(lat|Lat|Lda|Ling|Lit|liv|loc|log|Lóg|long)\.\s?
\b(m|mai|mar|masc|Mat|máx|Mecân|[Mm]ed|Mil|mín|mult|Mús)\.\s?
\b(n|N|Náut|N.B|neg|neol|nov|num|núm)\.\s?
\b(ord|out)\.\s?
\b(pág|págs|Paleont|part|pass|[Pp]edag|pejor|pess|Pesc|p|Pe|p.f|pl|pleb|p.m|poét|[Pp]olít|pop|pov|poss|p.p|p.p.m|pp|pref|prep|[Pp]rof|pron|P.S)\.\s?
\b(q.b|q.do|Q.E|Q.I|ql)\.\s?
\b(R|rel|Relig|Rev)\.\s?
\b(S|S.A|set|símb|S. ?M|[Ss]ra?s?|[Ss]rta|suf|superl)\.\s?
\b(t|tip|Tip|tít|top|[Tt]opogr|tr|trad|Trás-os-M|trim)\.\s?
\b(Univ)\.\s?
\b(v|V|vd|vid|voc|vol|V.S|vs|vulg)\.\s?
\b(Zool)\.\s?
\bs([eé]c)?\.\s?
[IVXDMCL]+
\b(Mr|Mrs|No|pp|St|Jr|Bros|etc|vs|esp|[Ff]ig|PhD|al|cf|Inc|Ms|Gen|Sen|Prof|Corp|Co|Ltd)\.\s?
\b(sp|spp)\.\s?
\b[A-ZÀÉÈÍÓÒÚ]\.\s?
\b[ad]\.\s?
C\.
p\.\s\?
d\.
p\.\s\?
ex\.
P\.\s?
S\.
\bP[Hh]\.\s?
D\.?
V\.\s?
Rev\.
v\.\s?
g\.
\s\p{L}\.\s?
\p{L}\.
\b(\p{L}\.)+[\p{Pe}\p{Pf}\p{Pd}"”']*\s
\p{Ll}
\b([\p{Lu}]{2}\.)+[\p{Pe}\p{Pf}\p{Pd}"”']*\s
\p{Ll}
\b([Ee]tc|m[aá]x|m[ií]n|aprox|\d+o)\.[\p{Pe}\p{Pf}\p{Pd}"”'’]*\s
\p{Ll}
\bet al\.[\p{Pe}\p{Pf}\p{Pd}"”']*\s
\b([Ee]sc|K[gm]s?|[mc]?[gml]s]|[Hh](rs)?)\.[\p{Pe}\p{Pf}\p{Pd}"”'’]*\s
\p{Ll}
\d+[a-z]\.\s?
\p{Lu}
\d+\.\s?
(e|ou|até)\s
['"“][\.!?…]['"”]\s
[^\s](\Q...\E|…)\s
\p{Ll}
[\(\)\[\]]\s
["”'’]\s
\p{Ll}
[\(\[][!?]{1,3}[\]\)]\s
[!?]{1,3}[\)\]]\s
[\.!?…]\s
[-–—],?\s\p{Ll}.+
\b(etc)\.\s?
\p{Lu}\p{Ll}*
[\.!?][\u0002|'|"|“|«|\)|\]|\}¹²³]?\s+
[\.!?…]['"”»\p{Pe}\u00BB\u201D]?\s*
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?…]\s
\p{Lu}\p{Ll}*
[^\s]:\s
['"«¡¿\p{Ps}\p{Pi}]\p{Lu}\p{Ll}*
\r?\n
\p{Lu}\p{Ll}*
\b(a\.c|a\.C|ad es|all|Amn|Arch|Avv|Bcc|Cav|c\.a|C\.A\.P|Cc|banc|post|c\.c\.p|c\.m|Co|c\.p|C\.P|C\.p\.r|corr|c\.s|c\.v)\.\s
\b(Chia\.mo|C\.so|Circ\.ne)\s
\b(d\.C|Dott|Dr|ecc|Egr|e\.p\.c|fatt|FF\.AA|FF\.SS|Geom|Gen|g|gg|Id|Ing|int|lett)\.\s
\b(Dott\.ssa|Egr\.i|Egr\.ia|F\.lli|Gent\.mo|Gent\.mi|Gent\.ma|Gent\.me|Ill\.mo|L\.go)\s
\b(Mo|Mons|N\.B|n|ogg|On|p|pag|par|pp|p\.c|p\.c\.c|p\.es|p\.f|p\.r|P\.S|p\.v|P\.T|Prof)\.\s
\b(P\.zza|P\.le|Preg\.mo|Prof\.ssa)\s
\b(R|racc|Rag|Rev|ric|Rif|R\.P|R\.S\.V\.P|S\.A|S\. acc|S\.B\.F|seg|sgg|ss|S|Ss|Sig|Sigg|s\.n\.c|Soc|S\.p\.A|Spett|S\.P\.M|S\.r\.l)\.\s
\b(Sig\.na|Sig\.ra|Stim\.mo)\s
\b(tel|u\.s|V|V\.P|v\.r|v\.s)\.\s
\b(V\.le)\s
\b(abbr|acron|agg|art|avv|card|compar|conf|cong|det|dim|f|fonosimb|ger|impers|indef|indet|inter|intr|inv|lat|loc|m|n|num|ord|p|pers|pl|pass|pres|pref|prep|pron|ponom|rel|s|sost|simb|suff|ter|tr|v|var)\.\s
[\.!?…][\u00BB\u2019\u201D\u203A"'\p{Pe}\u0002¹²³]*\s
[\.!?…]['"\u00BB\u2019\u201D\u203A\p{Pe}\u0002]*
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?…]\s
\p{Lu}\p{Ll}
\bஎ\.கா\.\s
\b(ஜன|பிப்|மார்|ஏப்|ஆக|செப்|அக்|நவ|டிச)\.\s
\b(ரூ|ரி\.ம|பக்)\.\s
\p{N}
\b(கி\.பி|கி\.மு)\.\s
\p{N}
\b(ஐ\.நா|தி\.மு\.க|அ\.இ\.அ\.தி\.மு\.க|அ\.தி\.மு\.க|ம\.தி\.மு\.க|ம\.இ\.கா|இ\.ஆ\.ப|ஐ\.ஏ\.எஸ்|எம்\.பி|எம்\.எல்\.ஏ|எம்\.ஜி\.ஆர்|டி\.எம்\.எஸ்)\.\s
\bபி\.கு\.:?\s
\b(பி\.இ|பி\.ஏ|ஏம்\.பி\.பி\.எஸ்|பி\.ஏ\.பி\.எல்|எம்\.ஏ|எம்\.எஸ்\.சி|எம்\.இ|எம்.லிட்|பி\.எச்\.டி)\.\s
[\.!?…][\u00BB\u2019\u201D\u203A"'\p{Pe}\u0002\]\}¹²³]*\s
[\.!?…][\u00BB\u2019\u201D\u203A"'\p{Pe}\u0002¹²³]*\s
[\.!?…]['"\u00BB\u2019\u201D\u203A\p{Pe}\u0002]*
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?…]\s
\p{Lu}\p{Ll}
\b(نه|بله)\!\s
\p{N}
[\[\(]*…[\]\)]*
\p{Ll}
\p{Ps}[!?؟]+\p{Pe}
[\.!?؟…]+\p{Pe}
\p{Ll}
[«»"”']\s*
\s*\p{Ll}
[«'"„][\.!?؟…]['"”»]\s
\b\p{L}\.\s
\p{L}\.\s
\b\p{L}\.
\p{L}\.
[^,،][\s]\p{L}{2}\.\s
\p{N}+\)\s
[\.\s]\p{L}{1,2}\.\s
[\p{N}\p{Ll}]
[\[\(]*\.\.\.[\]\)]*
[^\p{Lu}]
\b\p{Lu}\.\s\p{Lu}\.\s
\b\p{Lu}\.\p{Lu}\.\s
[^\.]\s[ضصثقفغعهخحجچشسیبلاتنمکگ\ظطزرذدپوًٌٍَُِّْA-Z]\.\s
\(\p{Ll}+\.\s
[\.!?؟…][«»\u00BB\u2019\u201D\u203A"'\p{Pe}\u0002¹²³]*\s
[\.!?؟…][«»'"\u00BB\u2019\u201D\u203A\p{Pe}\u0002]*
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?؟…]\s
\p{Lu}\p{Ll}
[^-\p{L}'’]\p{L}[\.!?…]['|"|“|«|\)|\]|\}]?\s
\b\p{L}\.
\s\p{L}\.\s
\p{L}\.
[\[\(]?\.\.\.[\]\)]?\s
\p{Ll}
['"„][\.!?…]['"“]\s
["'“],\s
\p{Ll}
\s([\.!?]{1,3}|…)['|"|“|«|\)|\]|\}]?\s
\b\d+\.\s
\p{Ll}|\p{Lu}{2,}
[\(\[][!?]{1,3}[\]\)]\s
[!?]{1,3}[\)\]]\s
[\s ][IVX]+\s
[^\p{Lu}]+
\d+\.\s
(и|или|до)\s
\d+\.\s
јануар|јануара|фебруар|фебруара|март|марта|април|априла|мај|маја|јун|јуна|јул|јула|август|августа|септембар|септембра|октобар|октобра|новембар|новембра|децембар|децембра
\d+\.\s
степен(у)
\b(versch|d|Übers|usw|Ab[hkts]|ahd|Akk|aktual|allg|alltagsspr|altdt|alttest|amerikan|Anh|Ank|Anm|Art|Az|Bat|bayr|Bd|Bde|bearb|Bed|Bem|bes|bez|Bez|Bhf|bspw|btto|bw|bzw|pot)\.\s
\b(одн|тј)\.\s+
[\.!?…][\u0002|'|"|“|\)|\]|\}¹²³]?\s+
[\.!?…]['"“\p{Pe}\u00BB\u201D]?
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?…]\s
\p{Lu}\p{Ll}
\bPh\.
D\.
\b\p{L}\.
\s\p{L}\.\s
\p{L}\.
['"][\.!?\u0085]['"]\s
["']\s
\p{Ll}
(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Sept|Oct|Nov|Dec)\.\s
\d\d(\d\d)?
(Ean|Fea|Már|Aib|Bea|Mei|Iúl|Lún|M\.?Fr|D\.?Fr|Sam|Nol)\.\s
\d\d(\d\d)?
\b(Mr|Mrs|Ms|No|pp|St|no|Sr|Jr|Bros|etc|vs|esp|[Ff]ig|Jan|Feb|Mar|Apr|Jun|Jul|Aug|Sep|Sept|Oct|Okt|Nov|Dec|PhD|al|cf|Inc|Ms|Gen|Sen|Prof|Corp|Co|Ltd)\.\s
\b(sp|spp)\.\s
([Ll]ch|[Ll]gh|[Uu]imh)\.\s
\d
\.i\.\s
Msc\.\s
Uas\.\s
Teo\.\s
m\.sh\.\s
[\.!?\u0085][\u0002|'|"|«|\)|\]|\}¹²³]?\s+
[\.!?\u0085]['"\p{Pe}\u00BB\u201D]?
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?\u0085]\s
\p{Lu}\p{Ll}
\bwww\.
\w
[\.!?]
\S*@
\bwww\.
\w
[\[\(]*…[\]\)]*
\p{Ll}
\p{Ps}[!?؟]+\p{Pe}
[\.!?؟…]+\p{Pe}
\p{Ll}
[«»"”']\s*
\s*\p{Ll}
[«'"„][\.!?؟…]['"”»]\s
\b\p{L}\.\s
\p{L}\.\s
\b\p{L}\.
\p{L}\.
[^,،][\s]\p{L}{2}\.\s
\p{N}+\)\s
[\.\s]\p{L}{1,2}\.\s
[\p{N}\p{Ll}]
[\[\(]*\.\.\.[\]\)]*
[^\p{Lu}]
\b\p{Lu}\.\s\p{Lu}\.\s
\b\p{Lu}\.\p{Lu}\.\s
[^\.]\s[ابتقجحخدذصضعغفقكلمنهوىيءةأ١٢٣٤٥٦٧٨٩٠A-Z]\.\s
[^\.]\s[\u064B\u064C\u064D\u064E\u064F\u0650\u0651\u0652\u0653\u0654\u0655\u0656\u0640]\.\s
\(\p{Ll}+\.\s
[\.!?؟…][«»\u00BB\u2019\u201D\u203A"'\p{Pe}\u0002¹²³]*\s
[\.!?؟…][«»'"\u00BB\u2019\u201D\u203A\p{Pe}\u0002]*
\p{Lu}[^\p{Lu}]
\s\p{L}[\.!?؟…]\s
\p{Lu}\p{Ll}