1- # https://trac.openstreetmap.org/browser/subversion/applications/editors/josm/plugins/ tag2link/resources/tag2link_sources.xml?rev=30720&format=txt
1+ # https://raw.githubusercontent.com/JOSM/ tag2link/master/index.json
22
3- import re
4- import xml .sax
5- from typing import Any , Dict , List
6- from xml .sax .xmlreader import AttributesImpl
7-
8-
9- class Exact (xml .sax .handler .ContentHandler ):
10- def __init__ (self ):
11- self .rules : List [Dict [str , Any ]] = []
12- self .val : Regex = re .compile ("(%[^%]+%|\{[^}]+})" ) # noqa
13-
14- def unposix (self , regex : str ) -> str :
15- regex = regex .replace ("\p{Lower}" , "[a-z]" ) # noqa
16- regex = regex .replace ("\p{Upper}" , "[A-Z]" ) # noqa
17- regex = regex .replace ("\p{Digit}" , "[0-9]" ) # noqa
18- return regex
19-
20- def startElement (self , name : str , attrs : AttributesImpl ) -> None :
21- if name == "rule" :
22- self .rules .append ({"conditions" : [], "link" : None })
23- elif name == "condition" :
24- self .rules [- 1 ]["conditions" ].append (
25- {
26- "kk" : attrs ["k" ],
27- "k" : re .compile ("^" + self .unposix (attrs ["k" ]) + "$" ),
28- "v" : (
29- re .compile ("^" + self .unposix (attrs ["v" ]) + "$" )
30- if "v" in attrs
31- else None
32- ),
33- "id" : attrs ["id" ] if "id" in attrs else None ,
34- }
35- )
36- elif name == "link" :
37- link = attrs ["href" ]
38- subs = []
39- if "%" in link or "{" in link :
40- for valmatch in self .val .finditer (link ):
41- sub = []
42- v = valmatch .group (1 )
43- link = link .replace (v , "%s" , 1 )
44- var = v [1 :- 1 ].split (":" )
45- for ll in var :
46- if "." not in ll and ll != "v" and ll != "k" :
47- vv = ll
48- else :
49- vv = ll .split ("." )
50- if vv [0 ] in ("k" , "v" ):
51- vv = [None ] + vv
52- if len (vv ) == 2 :
53- vv .append (0 )
54- else :
55- vv [2 ] = int (vv [2 ])
56- sub .append (vv )
57- subs .append (sub )
58- self .rules [- 1 ]["link" ] = {"url" : link , "subs" : subs }
3+ import json
4+ from typing import Dict , List
595
606
617class tag2link :
628 def __init__ (self , rulesFiles : str ):
63- parser = xml .sax .make_parser ()
64- handler = Exact ()
65- parser .setContentHandler (handler )
66- parser .parse (open (rulesFiles , "r" , encoding = "utf-8" ))
67- self .rules = handler .rules
68- self .all = re .compile (".*" )
9+ rules_json = json .load (open (rulesFiles , "r" , encoding = "utf-8" ))
10+ self .rules : Dict [str , str ] = dict (
11+ map (
12+ lambda rule : [
13+ rule ["key" ][4 :],
14+ rule ["url" ],
15+ ],
16+ filter (lambda rule : rule ["key" ].startswith ("Key:" ), rules_json ),
17+ )
18+ )
19+ print (self .rules )
6920
70- def checkTags (self , tags : Dict [str , str ]) -> Dict [str , str ]:
71- try :
72- urls : Dict [str , str ] = {}
73- for rule in self .rules :
74- valid = True
75- id = {}
76- for condition in rule ["conditions" ]:
77- match = False
78- for key in tags .keys ():
79- kmatch = condition ["k" ].match (key )
80- if kmatch :
81- id [condition ["id" ]] = {"k" : kmatch }
82- if condition ["v" ] is None :
83- vmatch = self .all .match (tags [key ])
84- id [condition ["id" ]]["v" ] = vmatch
85- match = True
86- break
87- else :
88- vmatch = condition ["v" ].match (tags [key ])
89- if vmatch :
90- id [condition ["id" ]]["v" ] = vmatch
91- match = True
92- break
93- if not match :
94- valid = False
95- break
96- if valid :
97- replace = []
98- for sub in rule ["link" ]["subs" ]:
99- for v in sub :
100- if isinstance (v , str ):
101- replace .append (v )
102- break
103- else :
104- val = id [v [0 ]][v [1 ]].group (v [2 ])
105- if val :
106- replace .append (val )
107- break
108- ret = rule ["link" ]["url" ] % tuple (replace )
109- if "://" not in ret :
110- ret = "http://" + ret
111- urls [id [rule ["link" ]["subs" ][0 ][0 ][0 ]]["k" ].group (0 )] = ret
112- return urls
113- except Exception :
114- return {}
21+ def addLinks (self , tags : Dict [str , str ]) -> List [Dict [str , str ]]:
22+ links = []
23+ for key , value in tags .items ():
24+ links .append ({"k" : key , "v" : value })
25+ if key in self .rules :
26+ links [- 1 ]["vlink" ] = self .rules [key ].replace ("$1" , tags [key ])
27+ return links
11528
11629
11730if __name__ == "__main__" :
118- t2l = tag2link ("tag2link_sources.xml " )
119- print (t2l .checkTags ({"oneway" : "yes" }))
120- print (t2l .checkTags ({"url" : "plop.com" }))
121- print (t2l .checkTags ({"url" : "http://plop.com" }))
122- print (t2l .checkTags ({"ref:UAI" : "123" }))
31+ t2l = tag2link ("tag2link_sources.json " )
32+ print (t2l .addLinks ({"oneway" : "yes" }))
33+ print (t2l .addLinks ({"url" : "plop.com" }))
34+ print (t2l .addLinks ({"url" : "http://plop.com" }))
35+ print (t2l .addLinks ({"ref:UAI" : "123" }))
12336 print (
124- t2l .checkTags (
37+ t2l .addLinks (
12538 {"man_made" : "survey_point" , "source" : "©IGN 2012" , "ref" : "1234567 - A" }
12639 )
12740 )
12841 print (
129- t2l .checkTags (
42+ t2l .addLinks (
13043 {
13144 "url" : "span://bad" ,
13245 "man_made" : "survey_point" ,
@@ -135,7 +48,7 @@ def checkTags(self, tags: Dict[str, str]) -> Dict[str, str]:
13548 }
13649 )
13750 )
138- print (t2l .checkTags ({"wikipedia:fr" : "toto" }))
139- print (t2l .checkTags ({"wikipedia" : "fr:toto" }))
140- print (t2l .checkTags ({"wikipedia" : "toto" }))
141- print (t2l .checkTags ({"source" : "source" , "source:url" : "http://example.com" }))
51+ print (t2l .addLinks ({"wikipedia:fr" : "toto" }))
52+ print (t2l .addLinks ({"wikipedia" : "fr:toto" }))
53+ print (t2l .addLinks ({"wikipedia" : "toto" }))
54+ print (t2l .addLinks ({"source" : "source" , "source:url" : "http://example.com" }))
0 commit comments