1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
|
# ScintillaData.py - implemented 2013 by Neil Hodgson neilh@scintilla.org
# Released to the public domain.
# Common code used by Scintilla and SciTE for source file regeneration.
# The ScintillaData object exposes information about Scintilla as properties:
# Version properties
# version
# versionDotted
# versionCommad
#
# Date last modified
# dateModified
# yearModified
# mdyModified
# dmyModified
# myModified
#
# Information about lexers and properties defined in lexers
# lexFiles
# sorted list of lexer files
# lexerModules
# sorted list of module names
# lexerProperties
# sorted list of lexer properties
# propertyDocuments
# dictionary of property documentation { name: document string }
# sclexFromName
# dictionary of SCLEX_* IDs { name: SCLEX_ID }
# fileFromSclex
# dictionary of file names { SCLEX_ID: file name }
# This file can be run to see the data it provides.
# Requires Python 2.7 or later
from __future__ import with_statement
import codecs, datetime, glob, os, sys, textwrap
import FileGenerator
def FindModules(lexFile):
modules = []
partLine = ""
with open(lexFile) as f:
for l in f.readlines():
l = l.rstrip()
if partLine or l.startswith("LexerModule"):
if ")" in l:
l = partLine + l
l = l.replace("(", " ")
l = l.replace(")", " ")
l = l.replace(",", " ")
parts = l.split()
modules.append([parts[1], parts[2], parts[4][1:-1]])
partLine = ""
else:
partLine = partLine + l
return modules
def FindLexersInXcode(xCodeProject):
lines = FileGenerator.ReadFileAsList(xCodeProject)
uidsOfBuild = {}
markersPBXBuildFile = ["Begin PBXBuildFile section", "", "End PBXBuildFile section"]
for buildLine in lines[FileGenerator.FindSectionInList(lines, markersPBXBuildFile)]:
# Occurs for each file in the build. Find the UIDs used for the file.
#\t\t[0-9A-F]+ /* [a-zA-Z]+.cxx in sources */ = {isa = PBXBuildFile; fileRef = [0-9A-F]+ /* [a-zA-Z]+ */; };
pieces = buildLine.split()
uid1 = pieces[0]
filename = pieces[2].split(".")[0]
uid2 = pieces[12]
uidsOfBuild[filename] = [uid1, uid2]
lexers = {}
markersLexers = ["/* Lexers */ =", "children", ");"]
for lexerLine in lines[FileGenerator.FindSectionInList(lines, markersLexers)]:
#\t\t\t\t[0-9A-F]+ /* [a-zA-Z]+.cxx */,
uid, _, rest = lexerLine.partition("/* ")
uid = uid.strip()
lexer, _, _ = rest.partition(".")
lexers[lexer] = uidsOfBuild[lexer]
return lexers
# Properties that start with lexer. or fold. are automatically found but there are some
# older properties that don't follow this pattern so must be explicitly listed.
knownIrregularProperties = [
"fold",
"styling.within.preprocessor",
"tab.timmy.whinge.level",
"asp.default.language",
"html.tags.case.sensitive",
"ps.level",
"ps.tokenize",
"sql.backslash.escapes",
"nsis.uservars",
"nsis.ignorecase"
]
def FindProperties(lexFile):
properties = {}
with open(lexFile) as f:
for l in f.readlines():
if ("GetProperty" in l or "DefineProperty" in l) and "\"" in l:
l = l.strip()
if not l.startswith("//"): # Drop comments
propertyName = l.split("\"")[1]
if propertyName.lower() == propertyName:
# Only allow lower case property names
if propertyName in knownIrregularProperties or \
propertyName.startswith("fold.") or \
propertyName.startswith("lexer."):
properties[propertyName] = 1
return properties
def FindPropertyDocumentation(lexFile):
documents = {}
with open(lexFile) as f:
name = ""
for l in f.readlines():
l = l.strip()
if "// property " in l:
propertyName = l.split()[2]
if propertyName.lower() == propertyName:
# Only allow lower case property names
name = propertyName
documents[name] = ""
elif "DefineProperty" in l and "\"" in l:
propertyName = l.split("\"")[1]
if propertyName.lower() == propertyName:
# Only allow lower case property names
name = propertyName
documents[name] = ""
elif name:
if l.startswith("//"):
if documents[name]:
documents[name] += " "
documents[name] += l[2:].strip()
elif l.startswith("\""):
l = l[1:].strip()
if l.endswith(";"):
l = l[:-1].strip()
if l.endswith(")"):
l = l[:-1].strip()
if l.endswith("\""):
l = l[:-1]
# Fix escaped double quotes
l = l.replace("\\\"", "\"")
documents[name] += l
else:
name = ""
for name in list(documents.keys()):
if documents[name] == "":
del documents[name]
return documents
def FindCredits(historyFile):
credits = []
stage = 0
with codecs.open(historyFile, "r", "utf-8") as f:
for l in f.readlines():
l = l.strip()
if stage == 0 and l == "<table>":
stage = 1
elif stage == 1 and l == "</table>":
stage = 2
if stage == 1 and l.startswith("<td>"):
credit = l[4:-5]
if "<a" in l:
title, a, rest = credit.partition("<a href=")
urlplus, bracket, end = rest.partition(">")
name = end.split("<")[0]
url = urlplus[1:-1]
credit = title.strip()
if credit:
credit += " "
credit += name + " " + url
credits.append(credit)
return credits
def ciCompare(a,b):
return cmp(a.lower(), b.lower())
def ciKey(a):
return a.lower()
def SortListInsensitive(l):
try: # Try key function
l.sort(key=ciKey)
except TypeError: # Earlier version of Python, so use comparison function
l.sort(ciCompare)
class ScintillaData:
def __init__(self, scintillaRoot):
# Discover verion information
with open(scintillaRoot + "version.txt") as f:
self.version = f.read().strip()
if len(self.version) == 3:
self.versionDotted = self.version[0] + '.' + self.version[1] + '.' + \
self.version[2]
self.versionCommad = self.version[0] + ', ' + self.version[1] + ', ' + \
self.version[2] + ', 0'
else:
self.versionDotted = self.version[0] + '.' + self.version[1:3] + '.' + \
self.version[3]
self.versionCommad = self.version[0] + ', ' + self.version[1:3] + ', ' + \
self.version[3] + ', 0'
with open(scintillaRoot + "doc/index.html") as f:
self.dateModified = [l for l in f.readlines() if "Date.Modified" in l]\
[0].split('\"')[3]
# 20130602
# index.html, SciTE.html
dtModified = datetime.datetime.strptime(self.dateModified, "%Y%m%d")
self.yearModified = self.dateModified[0:4]
monthModified = dtModified.strftime("%B")
dayModified = "%d" % dtModified.day
self.mdyModified = monthModified + " " + dayModified + " " + self.yearModified
# May 22 2013
# index.html, SciTE.html
self.dmyModified = dayModified + " " + monthModified + " " + self.yearModified
# 22 May 2013
# ScintillaHistory.html -- only first should change
self.myModified = monthModified + " " + self.yearModified
# Find all the lexer source code files
lexFilePaths = glob.glob(scintillaRoot + "lexers/Lex*.cxx")
SortListInsensitive(lexFilePaths)
self.lexFiles = [os.path.basename(f)[:-4] for f in lexFilePaths]
self.lexerModules = []
lexerProperties = set()
self.propertyDocuments = {}
self.sclexFromName = {}
self.fileFromSclex = {}
for lexFile in lexFilePaths:
modules = FindModules(lexFile)
for module in modules:
self.sclexFromName[module[2]] = module[1]
self.fileFromSclex[module[1]] = lexFile
if module[0] not in self.lexerModules:
self.lexerModules.append(module[0])
for k in FindProperties(lexFile).keys():
lexerProperties.add(k)
documents = FindPropertyDocumentation(lexFile)
for k in documents.keys():
if k not in self.propertyDocuments:
self.propertyDocuments[k] = documents[k]
SortListInsensitive(self.lexerModules)
self.lexerProperties = list(lexerProperties)
SortListInsensitive(self.lexerProperties)
self.lexersXcode = FindLexersInXcode(scintillaRoot + "cocoa/ScintillaFramework/ScintillaFramework.xcodeproj/project.pbxproj")
self.credits = FindCredits(scintillaRoot + "doc/ScintillaHistory.html")
def printWrapped(text):
print(textwrap.fill(text, subsequent_indent=" "))
if __name__=="__main__":
sci = ScintillaData("../")
print("Version %s %s %s" % (sci.version, sci.versionDotted, sci.versionCommad))
print("Date last modified %s %s %s %s %s" % (
sci.dateModified, sci.yearModified, sci.mdyModified, sci.dmyModified, sci.myModified))
printWrapped(str(len(sci.lexFiles)) + " lexer files: " + ", ".join(sci.lexFiles))
printWrapped(str(len(sci.lexerModules)) + " lexer modules: " + ", ".join(sci.lexerModules))
#~ printWrapped(str(len(sci.lexersXcode)) + " Xcode lexer references: " + ", ".join(
#~ [lex+":"+uids[0]+","+uids[1] for lex, uids in sci.lexersXcode.items()]))
print("Lexer name to ID:")
lexNames = sorted(sci.sclexFromName.keys())
for lexName in lexNames:
sclex = sci.sclexFromName[lexName]
fileName = os.path.basename(sci.fileFromSclex[sclex])
print(" " + lexName + " -> " + sclex + " in " + fileName)
printWrapped("Lexer properties: " + ", ".join(sci.lexerProperties))
print("Lexer property documentation:")
documentProperties = list(sci.propertyDocuments.keys())
SortListInsensitive(documentProperties)
for k in documentProperties:
print(" " + k)
print(textwrap.fill(sci.propertyDocuments[k], initial_indent=" ",
subsequent_indent=" "))
print("Credits:")
for c in sci.credits:
if sys.version_info[0] == 2:
print(" " + c.encode("utf-8"))
else:
sys.stdout.buffer.write(b" " + c.encode("utf-8") + b"\n")
|
