summaryrefslogtreecommitdiffhomepage
path: root/dlang/src/ocda/zip.d
blob: 1b4041a99c5542bd4c36f363e41243d36b79c533 (plain)
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
/+
- Name: SisuDoc Spine, Doc Reform [a part of]
  - Description: documents, structuring, processing, publishing, search
    - static content generator

  - Author: Ralph Amissah
    [ralph.amissah@gmail.com]

  - Copyright: (C) 2015 (continuously updated, current 2026) Ralph Amissah, All Rights Reserved.

  - License: AGPL 3 or later:

    Spine (SiSU), a framework for document structuring, publishing and
    search

    Copyright (C) Ralph Amissah

    This program is free software: you can redistribute it and/or modify it
    under the terms of the GNU AFERO General Public License as published by the
    Free Software Foundation, either version 3 of the License, or (at your
    option) any later version.

    This program is distributed in the hope that it will be useful, but WITHOUT
    ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
    FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
    more details.

    You should have received a copy of the GNU General Public License along with
    this program. If not, see [https://www.gnu.org/licenses/].

    If you have Internet connection, the latest version of the AGPL should be
    available at these locations:
    [https://www.fsf.org/licensing/licenses/agpl.html]
    [https://www.gnu.org/licenses/agpl.html]

  - Spine (by Doc Reform, related to SiSU) uses standard:
    - docReform markup syntax
      - standard SiSU markup syntax with modified headers and minor modifications
    - docReform object numbering
      - standard SiSU object citation numbering & system

  - Homepages:
    [https://www.sisudoc.org]
    [https://www.doc-reform.org]

  - Git
    [https://git.sisudoc.org/]

+/
module ocda.zip;

/+ ↓ enough of the zip format to find one file in a pod and read it.
     .
     Not a zip library. A pod archive holds a handful of entries, spine
     writes them **stored** (uncompressed) so that the outer zstd frame does
     the compressing once over the whole thing, and what is wanted from it
     here is one named entry. So: read the central directory, find the
     entry, return its bytes.
     .
     Deflate is *refused rather than mishandled*. Phobos can inflate, but a
     library that says it read an entry it in fact skipped is worse than one
     that says it cannot, and spine's own archives do not need it.
+/

import std.algorithm : endsWith;
import std.conv : to;

class OcdaZipError : Exception {
  this(string msg) { super(msg); }
}

struct ZipEntry {
  string name;
  uint   method;        // 0 stored, 8 deflate
  uint   compressed;
  uint   uncompressed;
  uint   local_offset;
}

/+ ↓ the entries, from the central directory at the end of the file +/
ZipEntry[] zipEntries(const(ubyte)[] bytes) {
  enum uint eocd_sig = 0x06054b50;
  enum uint cd_sig   = 0x02014b50;
  if (bytes.length < 22) {
    throw new OcdaZipError("too short to be a zip archive");
  }
  /+ ↓ the end of central directory record is last, and may be followed by a
       comment of up to 65535 bytes, so it is searched for backwards +/
  ptrdiff_t eocd = -1;
  ptrdiff_t lowest = bytes.length > (22 + 65535) ? bytes.length - (22 + 65535) : 0;
  for (ptrdiff_t i = bytes.length - 22; i >= lowest; i--) {
    if (u32(bytes, i) == eocd_sig) { eocd = i; break; }
  }
  if (eocd < 0) {
    throw new OcdaZipError("no end of central directory record;"
      ~ " it does not look like a zip archive");
  }
  uint count  = u16(bytes, eocd + 10);
  uint offset = u32(bytes, eocd + 16);
  ZipEntry[] out_;
  size_t p = offset;
  foreach (_; 0 .. count) {
    if (p + 46 > bytes.length || u32(bytes, p) != cd_sig) {
      throw new OcdaZipError("central directory entry "
        ~ out_.length.to!string ~ " is malformed");
    }
    ZipEntry e;
    e.method       = u16(bytes, p + 10);
    e.compressed   = u32(bytes, p + 20);
    e.uncompressed = u32(bytes, p + 24);
    uint name_len  = u16(bytes, p + 28);
    uint extra_len = u16(bytes, p + 30);
    uint cmnt_len  = u16(bytes, p + 32);
    e.local_offset = u32(bytes, p + 42);
    e.name = cast(string) bytes[p + 46 .. p + 46 + name_len].idup;
    out_ ~= e;
    p += 46 + name_len + extra_len + cmnt_len;
  }
  return out_;
}

/+ ↓ one entry's bytes, from its local header +/
ubyte[] zipRead(const(ubyte)[] bytes, ZipEntry e) {
  enum uint local_sig = 0x04034b50;
  size_t p = e.local_offset;
  if (p + 30 > bytes.length || u32(bytes, p) != local_sig) {
    throw new OcdaZipError(e.name ~ ": local header is malformed");
  }
  uint name_len  = u16(bytes, p + 26);
  uint extra_len = u16(bytes, p + 28);
  size_t start = p + 30 + name_len + extra_len;
  size_t end   = start + e.compressed;
  if (end > bytes.length) {
    throw new OcdaZipError(e.name ~ ": runs past the end of the archive");
  }
  if (e.method != 0) {
    throw new OcdaZipError(e.name ~ ": compression method "
      ~ e.method.to!string ~ "; this reader takes only stored entries,"
      ~ " which is what spine writes");
  }
  return bytes[start .. end].dup;
}

/+ ↓ the first entry whose name ends this way, or none.
     Used to find media/abstraction/<uid>.<lang>.ssp without knowing the uid.
+/
ZipEntry[] zipFindSuffix(ZipEntry[] entries, string suffix) {
  ZipEntry[] out_;
  foreach (e; entries) {
    if (e.name.endsWith(suffix)) { out_ ~= e; }
  }
  return out_;
}

private uint u16(const(ubyte)[] b, size_t i) {
  return cast(uint) b[i] | (cast(uint) b[i + 1] << 8);
}

private uint u32(const(ubyte)[] b, size_t i) {
  return cast(uint) b[i]
    | (cast(uint) b[i + 1] << 8)
    | (cast(uint) b[i + 2] << 16)
    | (cast(uint) b[i + 3] << 24);
}