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
|
module ocda.load_db;
/+ ↓ build the model from a .ocda.db.
.
The point of this module is that it returns *the same value*
ocda.load_ssp returns from the same document's .ssp. A writer is then
a function from the model to bytes, and cannot tell which
serialisation it was given, exactly as spine's own writers cannot.
.
Written from the sisudoc-abstraction-format specification,
ocda-db-format-specification.md, whose section 4 gives the column by
column correspondence this module implements.
+/
import std.array : split;
import std.conv : to;
import std.string : strip;
import ocda.model;
import ocda.sqlite;
/+ ↓ the schema major this loader knows (specification section 2) +/
enum schema_major_read = "2";
class OcdaDbError : Exception {
this(string msg) { super(msg); }
}
/+ ↓ every language the database holds, in manifest order +/
struct DbLanguage {
int doc_id;
string lang;
string source_filename;
string ssp_digest;
}
DbLanguage[] dbLanguages(ref Db db) {
DbLanguage[] out_;
foreach (r; db.rows(
"SELECT id, lang, coalesce(source_filename,''), coalesce(ssp_digest,'')
FROM documents ORDER BY id")) {
out_ ~= DbLanguage(r[0].to!int, r[1], r[2], r[3]);
}
return out_;
}
/+ ↓ load one language of a database as the model.
lang == "" takes the first language the manifest gave.
+/
OcdaDocument loadDbFile(string path, string lang = "", bool any_version = false) {
auto db = Db.open(path);
scope(exit) { db.close(); }
if (!db.has("documents") || !db.has("objects") || !db.has("metadata")) {
throw new OcdaDbError(path ~ ": no documents/objects/metadata tables;"
~ " it does not look like a .ocda.db");
}
/+ ↓ specification sections 2 and 3.2: the rows describing the file rather
than a document in it are the only ones with doc_id null +/
string schema_version = db.one(
"SELECT value FROM metadata WHERE doc_id IS NULL AND key = 'schema.version'");
if (schema_version.length > 0 && !any_version) {
auto major = schema_version.split(".")[0];
if (major != schema_major_read) {
throw new OcdaDbError(path ~ " is schema v" ~ schema_version
~ ", this loader knows v" ~ schema_major_read ~ ".x");
}
}
auto languages = dbLanguages(db);
if (languages.length == 0) {
throw new OcdaDbError(path ~ ": no documents rows");
}
DbLanguage chosen = languages[0];
if (lang.length > 0) {
bool found = false;
foreach (l; languages) { if (l.lang == lang) { chosen = l; found = true; break; } }
if (!found) {
string have;
foreach (i, l; languages) { have ~= (i > 0 ? " " : "") ~ l.lang; }
throw new OcdaDbError(path ~ ": no language '" ~ lang ~ "'; it holds: " ~ have);
}
}
OcdaDocument doc;
doc.format_version = schema_version;
doc.source_filename = chosen.source_filename;
/+ ↓ @source of the .ssp corresponds to the documents row and the
source.digest metadata (specification section 5.1 of the .ssp, and
section 7 here) +/
doc.source["language"] = chosen.lang;
string languages_joined;
foreach (i, l; languages) { languages_joined ~= (i > 0 ? " " : "") ~ l.lang; }
doc.source["languages"] = languages_joined;
auto digest = db.one("SELECT value FROM metadata WHERE doc_id = "
~ chosen.doc_id.to!string ~ " AND key = 'source.digest'");
if (digest.length > 0) { doc.source["digest"] = digest; }
/+ ↓ @meta: every metadata row of this language that is not a source.*
property. source.* describes the artefact rather than the document
and lives in @source in the text form.
+/
foreach (r; db.rows("SELECT key, value FROM metadata WHERE doc_id = "
~ chosen.doc_id.to!string ~ " ORDER BY key")) {
if (r[0].length > 7 && r[0][0 .. 7] == "source.") { continue; }
doc.metadata[r[0]] = r[1];
}
/+ ↓ the objects, in document order within each section +/
foreach (r; db.rows(
"SELECT section, seq, ocn, is_a, coalesce(is_of_part,''),
coalesce(is_of_section,''), coalesce(is_of_type,''),
coalesce(heading_level,-1), coalesce(identifier,''),
coalesce(parent_ocn,0), coalesce(last_descendant_ocn,0),
coalesce(children,''), coalesce(ancestors,''),
coalesce(dummy_heading,0), coalesce(object_number_off,0),
coalesce(indent_base,0), coalesce(indent_hang,0),
coalesce(bullet,0), coalesce(lang,''),
coalesce(has_links,0), coalesce(has_notes_reg,0),
coalesce(has_notes_star,0), coalesce(has_images,0),
coalesce(segment,''), coalesce(segment_prev,''),
coalesce(segment_next,''), coalesce(anchor,''),
coalesce(segment_html_is,''),
coalesce(table_cols,0), coalesce(table_widths,''),
coalesce(table_aligns,''), coalesce(table_header,0),
coalesce(code_linenumbers,0),
coalesce(heading_ancestors_text,''), coalesce(sha256,''),
coalesce(text,''), id
FROM objects WHERE doc_id = " ~ chosen.doc_id.to!string
~ " ORDER BY CASE section
WHEN 'head' THEN 1 WHEN 'toc' THEN 2 WHEN 'body' THEN 3
WHEN 'endnotes' THEN 4 WHEN 'glossary' THEN 5
WHEN 'bibliography' THEN 6 WHEN 'bookindex' THEN 7
WHEN 'blurb' THEN 8 WHEN 'tail' THEN 9 ELSE 10 END, seq")) {
OcdaObject obj;
obj.section = r[0];
obj.ocn = r[2].to!int;
obj.is_a = r[3];
obj.part = r[4];
obj.own_section = (r[5] == r[0]) ? "" : r[5];
obj.is_of_type = r[6];
/+ ↓ the database holds the level as a number, the text form as the
letter or digit the markup wrote. Model section 4 is the mapping. +/
obj.heading_level = levelName(r[7].to!int);
obj.identifier = r[8];
obj.parent_ocn = r[9].to!int;
obj.last_descendant_ocn = r[10].to!int;
obj.children = jsonInts(r[11]);
obj.ancestors = jsonInts(r[12]);
obj.dummy_heading = (r[13] != "0");
obj.ocn_off = (r[14] != "0");
obj.indent_base = r[15].to!int;
obj.indent_hang = r[16].to!int;
obj.bullet = (r[17] != "0");
obj.lang = r[18];
obj.has_links = (r[19] != "0");
obj.has_notes_reg = (r[20] != "0");
obj.has_notes_star = (r[21] != "0");
obj.has_images = (r[22] != "0");
obj.segment = r[23];
obj.segment_prev = r[24];
obj.segment_next = r[25];
obj.anchor = r[26];
obj.segment_html_is = r[27];
obj.table_cols = r[28].to!int;
obj.table_widths = jsonWords(r[29]);
obj.table_aligns = jsonWords(r[30]);
obj.table_header = (r[31] != "0");
obj.code_linenumbers = (r[32] != "0");
obj.heading_ancestors_text = jsonJoined(r[33]);
obj.sha256 = r[34];
obj.text = r[35];
/+ ↓ the four repeatable properties of the text form are child tables
here (specification section 4) +/
string object_id = r[36];
foreach (i; db.rows("SELECT name, coalesce(sha256,''), coalesce(bytes,0),
coalesce(width,0), coalesce(height,0),
coalesce(missing,0)
FROM object_images WHERE object_id = " ~ object_id
~ " ORDER BY seq")) {
OcdaImage img;
img.name = i[0];
img.sha256 = i[1];
img.bytes = i[2].to!ulong;
img.width = i[3].to!int;
img.height = i[4].to!int;
img.missing = (i[5] != "0");
obj.images ~= img;
}
foreach (l; db.rows("SELECT url FROM object_links WHERE object_id = "
~ object_id ~ " ORDER BY seq")) {
obj.stow_link ~= l[0];
}
auto section = doc.sectionByName(r[0]);
if (section !is null) { *section ~= obj; }
}
return doc;
}
/+ ↓ model section 4: the eight levels and their indices +/
private string levelName(int index) {
switch (index) {
case 0: return "A";
case 1: return "B";
case 2: return "C";
case 3: return "D";
case 4: return "1";
case 5: return "2";
case 6: return "3";
case 7: return "4";
default: return "";
}
}
/+ ↓ the fixed width arrays are JSON in the database and space separated in
the text form (specification section 3.3) +/
private int[] jsonInts(string v) {
int[] out_;
foreach (w; jsonWords(v).split(" ")) {
if (w.length == 0) { continue; }
try { out_ ~= w.to!int; } catch (Exception) {}
}
return out_;
}
private string jsonWords(string v) {
string out_;
bool in_string = false;
foreach (c; v) {
switch (c) {
case '[': case ']': case ' ': break;
case '"': in_string = !in_string; break;
case ',': out_ ~= " "; break;
default: out_ ~= c; break;
}
}
return out_.strip;
}
/+ ↓ heading_ancestors_text is eight slots, joined with "|" in the text
form and a JSON array here +/
private string jsonJoined(string v) {
if (v.length == 0) { return ""; }
string out_;
bool in_string = false;
bool first = true;
string cur;
foreach (c; v) {
if (c == '"') {
in_string = !in_string;
if (!in_string) {
if (!first) { out_ ~= "|"; }
out_ ~= cur;
cur = "";
first = false;
}
continue;
}
if (in_string) { cur ~= c; }
}
return out_;
}
|