| … | |
… | |
| 32 | () |
32 | () |
| 33 | } |
33 | } |
| 34 | |
34 | |
| 35 | # "find interesting things"-patterns |
35 | # "find interesting things"-patterns |
| 36 | my @mark_patterns = ( |
36 | my @mark_patterns = ( |
|
|
37 | qr{ ([[:word:]]+) }x, |
|
|
38 | qr{ ([^[:space:]]+) }x, |
|
|
39 | |
| 37 | # common types of "parentheses" |
40 | # common types of "parentheses" |
|
|
41 | qr{ (?<![^[:space:]]) ` ([^‘’]+) ` (?![^[:space:]]) }x, |
| 38 | qr{ (?<![^[:space:]]) ‘ ([^‘’]+) ’ (?![^[:space]]) }x, |
42 | qr{ (?<![^[:space:]]) ‘ ([^‘’]+) ’ (?![^[:space:]]) }x, |
| 39 | qr{ (?<![^[:space:]]) ` ([^`']+) ' (?![^[:space]]) }x, |
43 | qr{ (?<![^[:space:]]) ` ([^`']+) ' (?![^[:space:]]) }x, |
|
|
44 | |
|
|
45 | qr{ (?<![^[:space:]]) ‘ ([^`']+) ’ (?![^[:space:]]) }x, |
|
|
46 | qr{ (?<![^[:space:]]) “ ([^`']+) ” (?![^[:space:]]) }x, |
|
|
47 | |
|
|
48 | qr{ (?<![^[:space:]]) (' [^[:space:]] [^']* ') }x, |
|
|
49 | qr{ (' [^']* [^[:space:]] ') (?![^[:space:]]) }x, |
| 40 | qr{ (?<![^[:space:]]) (" [^[:space:]] [^"]* ") }x, |
50 | qr{ (?<![^[:space:]]) (" [^[:space:]] [^"]* ") }x, |
| 41 | qr{ (" [^"]* [^[:space:]] ") (?![^[:space]]) }x, |
51 | qr{ (" [^"]* [^[:space:]] ") (?![^[:space:]]) }x, |
|
|
52 | |
| 42 | qr{ \< ([^<>[:space:]]+) \> }x, |
53 | qr{ \< ([^>]+) \> }x, |
| 43 | qr{ \{ ([^{}[:space:]]+) \} }x, |
|
|
| 44 | qr{ \[ ([^{}[:space:]]+) \] }x, |
|
|
| 45 | qr{ \( ([^()[:space:]]+) \) }x, |
54 | qr{ \( ([^)]+) \) }x, |
|
|
55 | qr{ \{ ([^}]+) \} }x, |
|
|
56 | qr{ \[ ([^]]+) \] }x, |
| 46 | |
57 | |
| 47 | # urls, just a heuristic |
58 | # urls, just a heuristic |
| 48 | qr{( |
59 | qr{( |
| 49 | (?:https?://|ftp://|news://|mailto:|file://|\bwww\.)[ab-zA-Z0-9\-\@;\/?:&=%\$_.+!*\x27(),~#]+ |
60 | (?:https?://|ftp://|news://|mailto:|file://|\bwww\.)[ab-zA-Z0-9\-\@;\/?:&=%\$_.+!*\x27(),~#]+ |
| 50 | [ab-zA-Z0-9\-\@;\/?:&=%\$_+*()~] # exclude some trailing characters (heuristic) |
61 | [ab-zA-Z0-9\-\@;\/?:&=%\$_+*()~] # exclude some trailing characters (heuristic) |
