Mercurial > p > roundup > code

comparison roundup/msgfmt.py @ 7772:6a1c1cd69582

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
chore: 'id' var shadows builtin, lint markers; sort imports Replaced 'id' variable with label and 'ids' variable with 'labels' for consistency.
author John Rouillard <rouilj@ieee.org>
date Sat, 02 Mar 2024 13:45:29 -0500
parents 4d2e1fa03f0f
children a9bac0cb4019
comparison
equal deleted inserted replaced
7771:4261449081be 7772:6a1c1cd69582
30 30
31 * msgfmt.PoSyntaxError if the po file has syntax errors 31 * msgfmt.PoSyntaxError if the po file has syntax errors
32 """ 32 """
33 33
34 import array 34 import array
35 from ast import literal_eval
36 import codecs 35 import codecs
37 from email.parser import HeaderParser
38 import struct 36 import struct
39 import sys 37 import sys
38 from ast import literal_eval
39 from email.parser import HeaderParser
40 40
41 PY3 = sys.version_info[0] == 3 41 PY3 = sys.version_info[0] == 3
42 if PY3: 42 if PY3:
43 def header_charset(s): 43 def header_charset(s):
44 p = HeaderParser() 44 p = HeaderParser()
53 return p.parsestr(s.encode('utf-8', 'ignore')).get_content_charset() 53 return p.parsestr(s.encode('utf-8', 'ignore')).get_content_charset()
54 54
55 from cStringIO import StringIO as BytesIO 55 from cStringIO import StringIO as BytesIO
56 # file is a type defined only under python 2. 56 # file is a type defined only under python 2.
57 # Flake8 when run in py3 flags this. 57 # Flake8 when run in py3 flags this.
58 FILE_TYPE = file # noqa: 821 58 FILE_TYPE = file # noqa: F821
59 59
60 60
61 class PoSyntaxError(Exception): 61 class PoSyntaxError(Exception):
62 """ Syntax error in a po file """ 62 """ Syntax error in a po file """
63 63
100 if first.startswith(codecs.BOM_UTF8): 100 if first.startswith(codecs.BOM_UTF8):
101 first = first.lstrip(codecs.BOM_UTF8) 101 first = first.lstrip(codecs.BOM_UTF8)
102 return [first] + output.readlines() 102 return [first] + output.readlines()
103 return output 103 return output
104 104
105 def add(self, context, id, string, fuzzy): 105 def add(self, context, label, string, fuzzy):
106 "Add a non-empty and non-fuzzy translation to the dictionary." 106 "Add a non-empty and non-fuzzy translation to the dictionary."
107 if string and not fuzzy: 107 if string and not fuzzy:
108 # The context is put before the id and separated by a EOT char. 108 # The context is put before the id and separated by a EOT char.
109 if context: 109 if context:
110 id = context + u'\x04' + id 110 label = context + u'\x04' + label
111 if not id: 111 if not label:
112 # See whether there is an encoding declaration 112 # See whether there is an encoding declaration
113 charset = header_charset(string) 113 charset = header_charset(string)
114 if charset: 114 if charset:
115 # decode header in proper encoding 115 # decode header in proper encoding
116 string = string.encode(self.encoding).decode(charset) 116 string = string.encode(self.encoding).decode(charset)
117 if not PY3: 117 if not PY3:
118 # undo damage done by literal_eval in Python 2.x 118 # undo damage done by literal_eval in Python 2.x
119 string = string.encode(self.encoding).decode(charset) 119 string = string.encode(self.encoding).decode(charset)
120 self.encoding = charset 120 self.encoding = charset
121 self.messages[id] = string 121 self.messages[label] = string
122 122
123 def generate(self): 123 def generate(self):
124 "Return the generated output." 124 "Return the generated output."
125 # the keys are sorted in the .mo file 125 # the keys are sorted in the .mo file
126 keys = sorted(self.messages.keys()) 126 keys = sorted(self.messages.keys())
127 offsets = [] 127 offsets = []
128 ids = strs = b'' 128 labels = strs = b''
129 for id in keys: 129 for label in keys:
130 msg = self.messages[id].encode(self.encoding) 130 msg = self.messages[label].encode(self.encoding)
131 id = id.encode(self.encoding) 131 label = label.encode(self.encoding)
132 # For each string, we need size and file offset. Each string is 132 # For each string, we need size and file offset. Each string is
133 # NUL terminated; the NUL does not count into the size. 133 # NUL terminated; the NUL does not count into the size.
134 offsets.append((len(ids), len(id), len(strs), 134 offsets.append((len(labels), len(label), len(strs),
135 len(msg))) 135 len(msg)))
136 ids += id + b'\0' 136 labels += label + b'\0'
137 strs += msg + b'\0' 137 strs += msg + b'\0'
138 output = b'' 138 output = b''
139 # The header is 7 32-bit unsigned integers. We don't use hash tables, 139 # The header is 7 32-bit unsigned integers. We don't use hash tables,
140 # so the keys start right after the index tables. 140 # so the keys start right after the index tables.
141 keystart = 7 * 4 + 16 * len(keys) 141 keystart = 7 * 4 + 16 * len(keys)
142 # and the values start after the keys 142 # and the values start after the keys
143 valuestart = keystart + len(ids) 143 valuestart = keystart + len(labels)
144 koffsets = [] 144 koffsets = []
145 voffsets = [] 145 voffsets = []
146 # The string table first has the list of keys, then the list of values. 146 # The string table first has the list of keys, then the list of values.
147 # Each entry has first the size of the string, then the file offset. 147 # Each entry has first the size of the string, then the file offset.
148 for o1, l1, o2, l2 in offsets: 148 for o1, l1, o2, l2 in offsets:
161 0, keystart) # size and offset of hash table 161 0, keystart) # size and offset of hash table
162 if PY3: 162 if PY3:
163 output += array.array("i", offsets).tobytes() 163 output += array.array("i", offsets).tobytes()
164 else: 164 else:
165 output += array.array("i", offsets).tostring() 165 output += array.array("i", offsets).tostring()
166 output += ids 166 output += labels
167 output += strs 167 output += strs
168 return output 168 return output
169 169
170 def get(self): 170 def get(self):
171 """ """ 171 """ """
182 section = None 182 section = None
183 fuzzy = 0 183 fuzzy = 0
184 msgid = msgstr = msgctxt = u'' 184 msgid = msgstr = msgctxt = u''
185 185
186 # Parse the catalog 186 # Parse the catalog
187 # ruff: noqa: E741 PLW2901 - 'l' var name ok; overwrite 'l' ok
187 lno = 0 188 lno = 0
188 for l in self.readPoData(): 189 for l in self.readPoData():
189 l = l.decode(self.encoding) 190 l = l.decode(self.encoding)
190 lno += 1 191 lno += 1
191 # If we get a comment line after a msgstr or a line starting with 192 # If we get a comment line after a msgstr or a line starting with
Roundup Issue Tracker: http://roundup-tracker.org/