Akron | 78f6714 | 2022-04-09 14:10:44 +0200 | [diff] [blame] | 1 | ! General rules that require certain language specific definitions |
| 2 | |
| 3 | ! A solution to the "(author): problem" may be to add ) at the end of any |
| 4 | ! string as a possible ending |
| 5 | define Years ["(" Digit+ (".") ")"] | ["[" Digit+ (".") "]"]; |
| 6 | |
| 7 | ! 20:00 Uhr, 00:12:25,34 |
| 8 | define Times [ ( [%0|1|2|3|4|5] ) Digit [ ":" [%0|1|2|3|4|5] Digit ]^{1,2} ( "," [ Digit ]^{1,3} ) ]; |
| 9 | |
| 10 | ! Emoticons |
| 11 | source all/emoticons.xfst |
| 12 | |
| 13 | ! XML sources |
| 14 | source all/xml.xfst |
| 15 | |
| 16 | ! XML entities |
| 17 | source all/entities.xfst |
| 18 | |
Akron | 6dcb6ce | 2022-04-09 16:09:51 +0200 | [diff] [blame^] | 19 | ! Arrows |
| 20 | define Arrows [Alldash ">" | "<" Alldash]; |
| 21 | |
Akron | 78f6714 | 2022-04-09 14:10:44 +0200 | [diff] [blame] | 22 | ! Technical protocols |
| 23 | source all/protocols.xfst |
| 24 | |
| 25 | ! Also supports |
| 26 | ! 19.4.2015, 19/4/2015 etc. |
| 27 | define DigitPunct ["_"|"-"|"."|","|Slash]; |
| 28 | define Num Digit+ [DigitPunct Digit+]* (Char+); |
| 29 | |
| 30 | ! ordinals |
| 31 | define Ord Digit ( Digit (Digit) ) %.; |
| 32 | |
| 33 | ! TODO: |
| 34 | ! floating point, serial, model numbers, ip addresses, etc. |
| 35 | ! every other segment must have at least one digit |
| 36 | |
| 37 | ! Omission words like "fu**ing!" |
| 38 | define Omission Char+ Asterisk Asterisk+ Char*; |
| 39 | |
| 40 | ! acronyms: U.S.A., I.B.M., etc. |
| 41 | ! use a post-filter to remove dots |
| 42 | define AcronymDep Letter %. Letter %. [Letter %.]+; |
| 43 | |
| 44 | |
| 45 | ! TODO: Name words with ' and ` |
| 46 | |
| 47 | ! Support ASCII elements, like |
| 48 | ! +---------------+ |
| 49 | ! <---->, -->, <-- |
| 50 | ! +---------------+ |
| 51 | ! <---> | Worker Node N | |
| 52 | ! +---------------+ |
| 53 | ! |============= Core =============| |
| 54 | |