home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
Chip 2005 February
/
CMCD0205.ISO
/
Software
/
Freeware
/
Multimedia
/
SubtitleWork
/
SubtitleWorkshop251.exe
/
OCRScripts
/
Default.ocr
next >
Wrap
Text File
|
2004-02-25
|
4KB
|
92 lines
<!----------------------------------------------->
<!-- Subtitle Workshop OCR Script file -->
<!-- Copyright ⌐ 2001-2004 URUSoft -->
<!-- http://www.urusoft.net -->
<!-- -->
<!-- Default values: -->
<!-- -->
<!-- UseRE = True (use Regular Expressions) -->
<!-- UseREOnlyToFind = True (put the part that -->
<!-- is not a RE between parenthesis!) -->
<!-- -->
<!-- If UseRE is set to false then you can use -->
<!-- the following parameters, otherwise they -->
<!-- will be ignored: -->
<!-- -->
<!-- CaseSensitive (Default = False) -->
<!-- WholeWord (Default = False) -->
<!-- PreserveCase (Default = False) -->
<!-- ----------------------------------------- -->
<!-- Regular Expressions make the OCR Scripts -->
<!-- extremely powerful. For details on their -->
<!-- use, refer to "Subtitle Workshop Manual" -->
<!-- or download a help file in the available -->
<!-- languages from: -->
<!-- http://www.regexpstudio.com/ -->
<!----------------------------------------------->
<SWOCR WordChars="0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ_±╤ßΘφ≤·┴╔═╙┌Σδ∩÷ⁿ">
<!-- Eg. "swaIIow" by "swallow" -->
<ERROR Find="[a-zß-·](II)" ReplaceBy="ll">
<ERROR Find="(II)[a-zß-·]" ReplaceBy="ll">
<!-- Replace all "l" by "I" in the middle of any uppercase word -->
<ERROR Find="[A-Z┴-┌](l)[A-Z┴-┌]" ReplaceBy="I">
<!-- Replace all "I" by "l" in the middle of any lowercase word -->
<ERROR Find="[a-zß-·](I)[a-zß-·]" ReplaceBy="l">
<!-- Replace all alone "l" to "I" -->
<ERROR Find="\b(l)\b" ReplaceBy="I">
<!-- I'II to I'll -->
<ERROR Find="['A-Z┴-┌](II)\s[a-zß-·]" ReplaceBy="ll">
<ERROR Find="['A-Z┴-┌](II)\s\W[a-zß-·]" ReplaceBy="ll">
<!-- "1 :", "2 :"... "n :" to "n:" -->
<ERROR Find="\d( :)" ReplaceBy=":">
<!-- ",,," or similar to "..." -->
<ERROR UseREOnlyToFind="False" Find=",{2,}" ReplaceBy="...">
<!-- "--" or more to "..." -->
<ERROR UseREOnlyToFind="False" Find="-{2,}" ReplaceBy="...">
<!-- Apostrophes ("\x22" is '"' character) -->
<ERROR Find="[┤`ôö]" ReplaceBy="'">
<ERROR UseREOnlyToFind="False" Find="''" ReplaceBy=""">
<!-- '"' more than two times together is replaced by only one '"' -->
<ERROR UseREOnlyToFind="False" Find="\x22{2,}" ReplaceBy=""">
<!-- Spaces after aphostrophes, eg. "I' d" to "I'd", "I' LL" to "I'LL", etc. -->
<ERROR Find="(?i)[A-Z┴-┌a-zß-·]('\s|\s')(ll|ve|s|m|d)\b" ReplaceBy="'">
<!-- F "Hasn 't" and "Hasn' t" -->
<ERROR Find="(?i)[A-Z┴-┌a-zß-·]('\s|\s')t\b" ReplaceBy="'">
<!-- Rare 'Spaces after aphostrophes' cases -->
<!-- "I 'II" -> "I'll" or "I' II" -> "I'll" -->
<ERROR Find="[A-Z┴-┌a-zß-·]('\sII|\s'II)\b" ReplaceBy="'ll">
<!-- Particular cases -->
<ERROR Find="\b(I)[aeiouß-·]" ReplaceBy="l">
<ERROR Find="\b[A-Z┴-┌](I)[a-zß-·]" ReplaceBy="l">
<ERROR Find="[AEOU┴╔╙┌](I)\b" ReplaceBy="l">
<ERROR Find="\b(l)[^aeiouyαß-·l]" ReplaceBy="I">
<ERROR Find="\b[TV](l)\b" ReplaceBy="I">
<!-- Rare cases -->
<!-- The name "Ian" -->
<ERROR Find="\b(lan)\b" ReplaceBy="Ian">
<!-- Location in USA "Iowa" -->
<ERROR Find="\b(lowa)\b" ReplaceBy="Iowa">
<!-- Fix zero and capital 'o' ripping mistakes -->
<ERROR Find="[0-9](O)" ReplaceBy="0">
<ERROR Find="[0-9](\.O)" ReplaceBy=".0">
<ERROR Find="[0-9](,O)" ReplaceBy=",0">
<ERROR Find="[A-Z](0)" ReplaceBy="O">
<ERROR Find="\b(0)[A-Za-z]" ReplaceBy="O">
<!-- Smart space after dot -->
<ERROR Find="[a-zß-·±Σ-ⁿ](\.)[^(\s\n\.\?\!)]" ReplaceBy=". ">
<!-- Space after last of some consecutive dots (eg. "...") -->
<ERROR Find="(\.\.)[^(\s\n\.\?\!)]" ReplaceBy=".. ">
<!-- Delete space after "..." that is at the beginning of the line. You may delete this line if you don't like it -->
<ERROR UseREOnlyToFind="False" Find="^(\.\.\.) " ReplaceBy="...">
</SWOCR>