aboutsummaryrefslogtreecommitdiff
path: root/.venv/lib/python3.12/site-packages/pypdf/_codecs/pdfdoc.py
diff options
context:
space:
mode:
authorS. Solomon Darnell2025-03-28 21:52:21 -0500
committerS. Solomon Darnell2025-03-28 21:52:21 -0500
commit4a52a71956a8d46fcb7294ac71734504bb09bcc2 (patch)
treeee3dc5af3b6313e921cd920906356f5d4febc4ed /.venv/lib/python3.12/site-packages/pypdf/_codecs/pdfdoc.py
parentcc961e04ba734dd72309fb548a2f97d67d578813 (diff)
downloadgn-ai-master.tar.gz
two version of R2R are hereHEADmaster
Diffstat (limited to '.venv/lib/python3.12/site-packages/pypdf/_codecs/pdfdoc.py')
-rw-r--r--.venv/lib/python3.12/site-packages/pypdf/_codecs/pdfdoc.py264
1 files changed, 264 insertions, 0 deletions
diff --git a/.venv/lib/python3.12/site-packages/pypdf/_codecs/pdfdoc.py b/.venv/lib/python3.12/site-packages/pypdf/_codecs/pdfdoc.py
new file mode 100644
index 00000000..306357a5
--- /dev/null
+++ b/.venv/lib/python3.12/site-packages/pypdf/_codecs/pdfdoc.py
@@ -0,0 +1,264 @@
+# PDFDocEncoding Character Set: Table D.2 of PDF Reference 1.7
+# C.1 Predefined encodings sorted by character name of another PDF reference
+# Some indices have '\u0000' although they should have something else:
+# 22: should be '\u0017'
+_pdfdoc_encoding = [
+ "\u0000",
+ "\u0001",
+ "\u0002",
+ "\u0003",
+ "\u0004",
+ "\u0005",
+ "\u0006",
+ "\u0007", # 0 - 7
+ "\u0008",
+ "\u0009",
+ "\u000a",
+ "\u000b",
+ "\u000c",
+ "\u000d",
+ "\u000e",
+ "\u000f", # 8 - 15
+ "\u0010",
+ "\u0011",
+ "\u0012",
+ "\u0013",
+ "\u0014",
+ "\u0015",
+ "\u0000",
+ "\u0017", # 16 - 23
+ "\u02d8",
+ "\u02c7",
+ "\u02c6",
+ "\u02d9",
+ "\u02dd",
+ "\u02db",
+ "\u02da",
+ "\u02dc", # 24 - 31
+ "\u0020",
+ "\u0021",
+ "\u0022",
+ "\u0023",
+ "\u0024",
+ "\u0025",
+ "\u0026",
+ "\u0027", # 32 - 39
+ "\u0028",
+ "\u0029",
+ "\u002a",
+ "\u002b",
+ "\u002c",
+ "\u002d",
+ "\u002e",
+ "\u002f", # 40 - 47
+ "\u0030",
+ "\u0031",
+ "\u0032",
+ "\u0033",
+ "\u0034",
+ "\u0035",
+ "\u0036",
+ "\u0037", # 48 - 55
+ "\u0038",
+ "\u0039",
+ "\u003a",
+ "\u003b",
+ "\u003c",
+ "\u003d",
+ "\u003e",
+ "\u003f", # 56 - 63
+ "\u0040",
+ "\u0041",
+ "\u0042",
+ "\u0043",
+ "\u0044",
+ "\u0045",
+ "\u0046",
+ "\u0047", # 64 - 71
+ "\u0048",
+ "\u0049",
+ "\u004a",
+ "\u004b",
+ "\u004c",
+ "\u004d",
+ "\u004e",
+ "\u004f", # 72 - 79
+ "\u0050",
+ "\u0051",
+ "\u0052",
+ "\u0053",
+ "\u0054",
+ "\u0055",
+ "\u0056",
+ "\u0057", # 80 - 87
+ "\u0058",
+ "\u0059",
+ "\u005a",
+ "\u005b",
+ "\u005c",
+ "\u005d",
+ "\u005e",
+ "\u005f", # 88 - 95
+ "\u0060",
+ "\u0061",
+ "\u0062",
+ "\u0063",
+ "\u0064",
+ "\u0065",
+ "\u0066",
+ "\u0067", # 96 - 103
+ "\u0068",
+ "\u0069",
+ "\u006a",
+ "\u006b",
+ "\u006c",
+ "\u006d",
+ "\u006e",
+ "\u006f", # 104 - 111
+ "\u0070",
+ "\u0071",
+ "\u0072",
+ "\u0073",
+ "\u0074",
+ "\u0075",
+ "\u0076",
+ "\u0077", # 112 - 119
+ "\u0078",
+ "\u0079",
+ "\u007a",
+ "\u007b",
+ "\u007c",
+ "\u007d",
+ "\u007e",
+ "\u0000", # 120 - 127
+ "\u2022",
+ "\u2020",
+ "\u2021",
+ "\u2026",
+ "\u2014",
+ "\u2013",
+ "\u0192",
+ "\u2044", # 128 - 135
+ "\u2039",
+ "\u203a",
+ "\u2212",
+ "\u2030",
+ "\u201e",
+ "\u201c",
+ "\u201d",
+ "\u2018", # 136 - 143
+ "\u2019",
+ "\u201a",
+ "\u2122",
+ "\ufb01",
+ "\ufb02",
+ "\u0141",
+ "\u0152",
+ "\u0160", # 144 - 151
+ "\u0178",
+ "\u017d",
+ "\u0131",
+ "\u0142",
+ "\u0153",
+ "\u0161",
+ "\u017e",
+ "\u0000", # 152 - 159
+ "\u20ac",
+ "\u00a1",
+ "\u00a2",
+ "\u00a3",
+ "\u00a4",
+ "\u00a5",
+ "\u00a6",
+ "\u00a7", # 160 - 167
+ "\u00a8",
+ "\u00a9",
+ "\u00aa",
+ "\u00ab",
+ "\u00ac",
+ "\u0000",
+ "\u00ae",
+ "\u00af", # 168 - 175
+ "\u00b0",
+ "\u00b1",
+ "\u00b2",
+ "\u00b3",
+ "\u00b4",
+ "\u00b5",
+ "\u00b6",
+ "\u00b7", # 176 - 183
+ "\u00b8",
+ "\u00b9",
+ "\u00ba",
+ "\u00bb",
+ "\u00bc",
+ "\u00bd",
+ "\u00be",
+ "\u00bf", # 184 - 191
+ "\u00c0",
+ "\u00c1",
+ "\u00c2",
+ "\u00c3",
+ "\u00c4",
+ "\u00c5",
+ "\u00c6",
+ "\u00c7", # 192 - 199
+ "\u00c8",
+ "\u00c9",
+ "\u00ca",
+ "\u00cb",
+ "\u00cc",
+ "\u00cd",
+ "\u00ce",
+ "\u00cf", # 200 - 207
+ "\u00d0",
+ "\u00d1",
+ "\u00d2",
+ "\u00d3",
+ "\u00d4",
+ "\u00d5",
+ "\u00d6",
+ "\u00d7", # 208 - 215
+ "\u00d8",
+ "\u00d9",
+ "\u00da",
+ "\u00db",
+ "\u00dc",
+ "\u00dd",
+ "\u00de",
+ "\u00df", # 216 - 223
+ "\u00e0",
+ "\u00e1",
+ "\u00e2",
+ "\u00e3",
+ "\u00e4",
+ "\u00e5",
+ "\u00e6",
+ "\u00e7", # 224 - 231
+ "\u00e8",
+ "\u00e9",
+ "\u00ea",
+ "\u00eb",
+ "\u00ec",
+ "\u00ed",
+ "\u00ee",
+ "\u00ef", # 232 - 239
+ "\u00f0",
+ "\u00f1",
+ "\u00f2",
+ "\u00f3",
+ "\u00f4",
+ "\u00f5",
+ "\u00f6",
+ "\u00f7", # 240 - 247
+ "\u00f8",
+ "\u00f9",
+ "\u00fa",
+ "\u00fb",
+ "\u00fc",
+ "\u00fd",
+ "\u00fe",
+ "\u00ff", # 248 - 255
+]
+
+assert len(_pdfdoc_encoding) == 256