diff options
Diffstat (limited to 'dlang/src/ocda/load_db.d')
| -rw-r--r-- | dlang/src/ocda/load_db.d | 115 |
1 files changed, 76 insertions, 39 deletions
diff --git a/dlang/src/ocda/load_db.d b/dlang/src/ocda/load_db.d index ffc28a8..f602da9 100644 --- a/dlang/src/ocda/load_db.d +++ b/dlang/src/ocda/load_db.d @@ -12,8 +12,10 @@ module ocda.load_db; column correspondence this module implements. +/ -import std.array : split; +import std.array : join, split; +import std.json : JSONType, parseJSON; import std.conv : to; +import std.algorithm : startsWith; import std.string : strip; import ocda.model; import ocda.sqlite; @@ -103,8 +105,31 @@ OcdaDocument loadDbFile(string path, string lang = "", bool any_version = false) +/ 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]; + string key = r[0]; + if (key.startsWith("source.")) { continue; } + /+ ↓ translation.ocn_aligned says whether the languages of this + document share one numbering. A .ocda.db can know it because it + holds every language; a .ssp is one language and cannot. So it is + a fact about the *file* rather than about the document, and putting + it in the document's metadata would let a writer tell which + serialisation it was handed, which is the one thing this library + exists to prevent. Left out until the model has a place for + collection-wide facts. + +/ + if (key.startsWith("translation.")) { continue; } + /+ ↓ the database has one metadata table where the text form has three + blocks, and tells them apart by a key prefix. Unprefixing them + here is what makes the two loaders give one model: a writer asks + doc.make["footer"] whichever serialisation it was handed, and + never doc.metadata["make.footer"]. + +/ + if (key.startsWith("make.")) { + doc.make[key["make.".length .. $]] = r[1].strip; + } else if (key.startsWith("doc_has.")) { + doc.doc_has[key["doc_has.".length .. $]] = r[1].strip; + } else { + doc.metadata[key] = r[1].strip; + } } /+ ↓ the objects, in document order within each section +/ @@ -215,51 +240,63 @@ private string levelName(int index) { } } -/+ ↓ the fixed width arrays are JSON in the database and space separated in - the text form (specification section 3.3) +/ +/+ ↓ the JSON columns, read as JSON. + . + The fixed width arrays are JSON in the database and space separated + (or "|" separated) in the text form. This was first written as a + character scan that threw away brackets and quotes, which is wrong the + moment a value holds an escape: Phobos' JSONValue.toString escapes + "/" as "\/", so every heading containing a slash came back with a + backslash in it. 36 of 36 documents differed on + heading_ancestors_text and nothing else had shown it. + . + So: parse. The values are small, there are few of them, and a real + parser is shorter than the scan it replaces. ++/ +private string[] jsonStrings(string v) { + if (v.length == 0) { return []; } + string[] out_; + try { + auto j = parseJSON(v); + if (j.type != JSONType.array) { return []; } + foreach (e; j.array) { + switch (e.type) { + case JSONType.string: out_ ~= e.str; break; + case JSONType.integer: out_ ~= e.integer.to!string; break; + case JSONType.uinteger: out_ ~= e.uinteger.to!string; break; + case JSONType.float_: out_ ~= e.floating.to!string; break; + case JSONType.true_: out_ ~= "true"; break; + case JSONType.false_: out_ ~= "false"; break; + default: out_ ~= ""; break; + } + } + } catch (Exception) { + return []; + } + return out_; +} + private int[] jsonInts(string v) { int[] out_; - foreach (w; jsonWords(v).split(" ")) { - if (w.length == 0) { continue; } - try { out_ ~= w.to!int; } catch (Exception) {} + foreach (s; jsonStrings(v)) { + if (s.length == 0) { continue; } + try { out_ ~= s.to!int; } catch (Exception) {} } return out_; } +/+ ↓ space separated in the text form: table_widths, table_aligns +/ 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; + return jsonStrings(v).join(" "); } /+ ↓ heading_ancestors_text is eight slots, joined with "|" in the text - form and a JSON array here +/ + form and a JSON array here. The empty slots are significant: they say + which levels the heading sits under, so the separators carry as much + as the text does. ++/ 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_; + auto parts = jsonStrings(v); + if (parts.length == 0) { return ""; } + return parts.join("|"); } |
