Coverage for /pythoncovmergedfiles/medio/medio/src/pdfminer.six/pdfminer/latin_enc.py: 100%

Shortcuts on this page

r m x   toggle line displays

j k   next/prev highlighted chunk

0   (zero) top of page

1   (one) first highlighted chunk

3 statements  

1"""Standard encoding tables used in PDF. 

2 

3This table is extracted from PDF Reference Manual 1.6, pp.925 

4 "D.1 Latin Character Set and Encodings" 

5 

6""" 

7 

8from typing import List, Optional, Tuple 

9 

10EncodingRow = Tuple[str, Optional[int], Optional[int], Optional[int], Optional[int]] 

11 

12ENCODING: List[EncodingRow] = [ 

13 # (name, std, mac, win, pdf) 

14 ("A", 65, 65, 65, 65), 

15 ("AE", 225, 174, 198, 198), 

16 ("Aacute", None, 231, 193, 193), 

17 ("Acircumflex", None, 229, 194, 194), 

18 ("Adieresis", None, 128, 196, 196), 

19 ("Agrave", None, 203, 192, 192), 

20 ("Aring", None, 129, 197, 197), 

21 ("Atilde", None, 204, 195, 195), 

22 ("B", 66, 66, 66, 66), 

23 ("C", 67, 67, 67, 67), 

24 ("Ccedilla", None, 130, 199, 199), 

25 ("D", 68, 68, 68, 68), 

26 ("E", 69, 69, 69, 69), 

27 ("Eacute", None, 131, 201, 201), 

28 ("Ecircumflex", None, 230, 202, 202), 

29 ("Edieresis", None, 232, 203, 203), 

30 ("Egrave", None, 233, 200, 200), 

31 ("Eth", None, None, 208, 208), 

32 ("Euro", None, None, 128, 160), 

33 ("F", 70, 70, 70, 70), 

34 ("G", 71, 71, 71, 71), 

35 ("H", 72, 72, 72, 72), 

36 ("I", 73, 73, 73, 73), 

37 ("Iacute", None, 234, 205, 205), 

38 ("Icircumflex", None, 235, 206, 206), 

39 ("Idieresis", None, 236, 207, 207), 

40 ("Igrave", None, 237, 204, 204), 

41 ("J", 74, 74, 74, 74), 

42 ("K", 75, 75, 75, 75), 

43 ("L", 76, 76, 76, 76), 

44 ("Lslash", 232, None, None, 149), 

45 ("M", 77, 77, 77, 77), 

46 ("N", 78, 78, 78, 78), 

47 ("Ntilde", None, 132, 209, 209), 

48 ("O", 79, 79, 79, 79), 

49 ("OE", 234, 206, 140, 150), 

50 ("Oacute", None, 238, 211, 211), 

51 ("Ocircumflex", None, 239, 212, 212), 

52 ("Odieresis", None, 133, 214, 214), 

53 ("Ograve", None, 241, 210, 210), 

54 ("Oslash", 233, 175, 216, 216), 

55 ("Otilde", None, 205, 213, 213), 

56 ("P", 80, 80, 80, 80), 

57 ("Q", 81, 81, 81, 81), 

58 ("R", 82, 82, 82, 82), 

59 ("S", 83, 83, 83, 83), 

60 ("Scaron", None, None, 138, 151), 

61 ("T", 84, 84, 84, 84), 

62 ("Thorn", None, None, 222, 222), 

63 ("U", 85, 85, 85, 85), 

64 ("Uacute", None, 242, 218, 218), 

65 ("Ucircumflex", None, 243, 219, 219), 

66 ("Udieresis", None, 134, 220, 220), 

67 ("Ugrave", None, 244, 217, 217), 

68 ("V", 86, 86, 86, 86), 

69 ("W", 87, 87, 87, 87), 

70 ("X", 88, 88, 88, 88), 

71 ("Y", 89, 89, 89, 89), 

72 ("Yacute", None, None, 221, 221), 

73 ("Ydieresis", None, 217, 159, 152), 

74 ("Z", 90, 90, 90, 90), 

75 ("Zcaron", None, None, 142, 153), 

76 ("a", 97, 97, 97, 97), 

77 ("aacute", None, 135, 225, 225), 

78 ("acircumflex", None, 137, 226, 226), 

79 ("acute", 194, 171, 180, 180), 

80 ("adieresis", None, 138, 228, 228), 

81 ("ae", 241, 190, 230, 230), 

82 ("agrave", None, 136, 224, 224), 

83 ("ampersand", 38, 38, 38, 38), 

84 ("aring", None, 140, 229, 229), 

85 ("asciicircum", 94, 94, 94, 94), 

86 ("asciitilde", 126, 126, 126, 126), 

87 ("asterisk", 42, 42, 42, 42), 

88 ("at", 64, 64, 64, 64), 

89 ("atilde", None, 139, 227, 227), 

90 ("b", 98, 98, 98, 98), 

91 ("backslash", 92, 92, 92, 92), 

92 ("bar", 124, 124, 124, 124), 

93 ("braceleft", 123, 123, 123, 123), 

94 ("braceright", 125, 125, 125, 125), 

95 ("bracketleft", 91, 91, 91, 91), 

96 ("bracketright", 93, 93, 93, 93), 

97 ("breve", 198, 249, None, 24), 

98 ("brokenbar", None, None, 166, 166), 

99 ("bullet", 183, 165, 149, 128), 

100 ("c", 99, 99, 99, 99), 

101 ("caron", 207, 255, None, 25), 

102 ("ccedilla", None, 141, 231, 231), 

103 ("cedilla", 203, 252, 184, 184), 

104 ("cent", 162, 162, 162, 162), 

105 ("circumflex", 195, 246, 136, 26), 

106 ("colon", 58, 58, 58, 58), 

107 ("comma", 44, 44, 44, 44), 

108 ("copyright", None, 169, 169, 169), 

109 ("currency", 168, 219, 164, 164), 

110 ("d", 100, 100, 100, 100), 

111 ("dagger", 178, 160, 134, 129), 

112 ("daggerdbl", 179, 224, 135, 130), 

113 ("degree", None, 161, 176, 176), 

114 ("dieresis", 200, 172, 168, 168), 

115 ("divide", None, 214, 247, 247), 

116 ("dollar", 36, 36, 36, 36), 

117 ("dotaccent", 199, 250, None, 27), 

118 ("dotlessi", 245, 245, None, 154), 

119 ("e", 101, 101, 101, 101), 

120 ("eacute", None, 142, 233, 233), 

121 ("ecircumflex", None, 144, 234, 234), 

122 ("edieresis", None, 145, 235, 235), 

123 ("egrave", None, 143, 232, 232), 

124 ("eight", 56, 56, 56, 56), 

125 ("ellipsis", 188, 201, 133, 131), 

126 ("emdash", 208, 209, 151, 132), 

127 ("endash", 177, 208, 150, 133), 

128 ("equal", 61, 61, 61, 61), 

129 ("eth", None, None, 240, 240), 

130 ("exclam", 33, 33, 33, 33), 

131 ("exclamdown", 161, 193, 161, 161), 

132 ("f", 102, 102, 102, 102), 

133 ("fi", 174, 222, None, 147), 

134 ("five", 53, 53, 53, 53), 

135 ("fl", 175, 223, None, 148), 

136 ("florin", 166, 196, 131, 134), 

137 ("four", 52, 52, 52, 52), 

138 ("fraction", 164, 218, None, 135), 

139 ("g", 103, 103, 103, 103), 

140 ("germandbls", 251, 167, 223, 223), 

141 ("grave", 193, 96, 96, 96), 

142 ("greater", 62, 62, 62, 62), 

143 ("guillemotleft", 171, 199, 171, 171), 

144 ("guillemotright", 187, 200, 187, 187), 

145 ("guilsinglleft", 172, 220, 139, 136), 

146 ("guilsinglright", 173, 221, 155, 137), 

147 ("h", 104, 104, 104, 104), 

148 ("hungarumlaut", 205, 253, None, 28), 

149 ("hyphen", 45, 45, 45, 45), 

150 ("i", 105, 105, 105, 105), 

151 ("iacute", None, 146, 237, 237), 

152 ("icircumflex", None, 148, 238, 238), 

153 ("idieresis", None, 149, 239, 239), 

154 ("igrave", None, 147, 236, 236), 

155 ("j", 106, 106, 106, 106), 

156 ("k", 107, 107, 107, 107), 

157 ("l", 108, 108, 108, 108), 

158 ("less", 60, 60, 60, 60), 

159 ("logicalnot", None, 194, 172, 172), 

160 ("lslash", 248, None, None, 155), 

161 ("m", 109, 109, 109, 109), 

162 ("macron", 197, 248, 175, 175), 

163 ("minus", None, None, None, 138), 

164 ("mu", None, 181, 181, 181), 

165 ("multiply", None, None, 215, 215), 

166 ("n", 110, 110, 110, 110), 

167 ("nbspace", None, 202, 160, None), 

168 ("nine", 57, 57, 57, 57), 

169 ("ntilde", None, 150, 241, 241), 

170 ("numbersign", 35, 35, 35, 35), 

171 ("o", 111, 111, 111, 111), 

172 ("oacute", None, 151, 243, 243), 

173 ("ocircumflex", None, 153, 244, 244), 

174 ("odieresis", None, 154, 246, 246), 

175 ("oe", 250, 207, 156, 156), 

176 ("ogonek", 206, 254, None, 29), 

177 ("ograve", None, 152, 242, 242), 

178 ("one", 49, 49, 49, 49), 

179 ("onehalf", None, None, 189, 189), 

180 ("onequarter", None, None, 188, 188), 

181 ("onesuperior", None, None, 185, 185), 

182 ("ordfeminine", 227, 187, 170, 170), 

183 ("ordmasculine", 235, 188, 186, 186), 

184 ("oslash", 249, 191, 248, 248), 

185 ("otilde", None, 155, 245, 245), 

186 ("p", 112, 112, 112, 112), 

187 ("paragraph", 182, 166, 182, 182), 

188 ("parenleft", 40, 40, 40, 40), 

189 ("parenright", 41, 41, 41, 41), 

190 ("percent", 37, 37, 37, 37), 

191 ("period", 46, 46, 46, 46), 

192 ("periodcentered", 180, 225, 183, 183), 

193 ("perthousand", 189, 228, 137, 139), 

194 ("plus", 43, 43, 43, 43), 

195 ("plusminus", None, 177, 177, 177), 

196 ("q", 113, 113, 113, 113), 

197 ("question", 63, 63, 63, 63), 

198 ("questiondown", 191, 192, 191, 191), 

199 ("quotedbl", 34, 34, 34, 34), 

200 ("quotedblbase", 185, 227, 132, 140), 

201 ("quotedblleft", 170, 210, 147, 141), 

202 ("quotedblright", 186, 211, 148, 142), 

203 ("quoteleft", 96, 212, 145, 143), 

204 ("quoteright", 39, 213, 146, 144), 

205 ("quotesinglbase", 184, 226, 130, 145), 

206 ("quotesingle", 169, 39, 39, 39), 

207 ("r", 114, 114, 114, 114), 

208 ("registered", None, 168, 174, 174), 

209 ("ring", 202, 251, None, 30), 

210 ("s", 115, 115, 115, 115), 

211 ("scaron", None, None, 154, 157), 

212 ("section", 167, 164, 167, 167), 

213 ("semicolon", 59, 59, 59, 59), 

214 ("seven", 55, 55, 55, 55), 

215 ("six", 54, 54, 54, 54), 

216 ("slash", 47, 47, 47, 47), 

217 ("space", 32, 32, 32, 32), 

218 ("space", None, 202, 160, None), 

219 ("space", None, 202, 173, None), 

220 ("sterling", 163, 163, 163, 163), 

221 ("t", 116, 116, 116, 116), 

222 ("thorn", None, None, 254, 254), 

223 ("three", 51, 51, 51, 51), 

224 ("threequarters", None, None, 190, 190), 

225 ("threesuperior", None, None, 179, 179), 

226 ("tilde", 196, 247, 152, 31), 

227 ("trademark", None, 170, 153, 146), 

228 ("two", 50, 50, 50, 50), 

229 ("twosuperior", None, None, 178, 178), 

230 ("u", 117, 117, 117, 117), 

231 ("uacute", None, 156, 250, 250), 

232 ("ucircumflex", None, 158, 251, 251), 

233 ("udieresis", None, 159, 252, 252), 

234 ("ugrave", None, 157, 249, 249), 

235 ("underscore", 95, 95, 95, 95), 

236 ("v", 118, 118, 118, 118), 

237 ("w", 119, 119, 119, 119), 

238 ("x", 120, 120, 120, 120), 

239 ("y", 121, 121, 121, 121), 

240 ("yacute", None, None, 253, 253), 

241 ("ydieresis", None, 216, 255, 255), 

242 ("yen", 165, 180, 165, 165), 

243 ("z", 122, 122, 122, 122), 

244 ("zcaron", None, None, 158, 158), 

245 ("zero", 48, 48, 48, 48), 

246]