diff options
Diffstat (limited to 'dlang/src/ocda/load_ssp.d')
| -rw-r--r-- | dlang/src/ocda/load_ssp.d | 337 |
1 files changed, 337 insertions, 0 deletions
diff --git a/dlang/src/ocda/load_ssp.d b/dlang/src/ocda/load_ssp.d new file mode 100644 index 0000000..34d156c --- /dev/null +++ b/dlang/src/ocda/load_ssp.d @@ -0,0 +1,337 @@ +module ocda.load_ssp; + +import std.algorithm : splitter, startsWith; +import std.array : array, split; +import std.conv : to, ConvException; +import std.file : readText; +import std.stdio : writeln; +import std.string : strip, stripLeft, indexOf; +import ocda.model; + +OcdaDocument parseSspFile(string filename) { + string content = readText(filename); + return parseSsp(content); +} + +OcdaDocument parseSsp(string content) { + OcdaDocument doc; + OcdaObject current_obj; + bool in_object = false; + /+ ↓ whether a text line has been seen for the object being read. + Not "is the text non-empty": an object whose first text line is blank + (a verse opening on an empty line, which the sample set has seven of) + would then lose it, the next line overwriting rather than appending. + +/ + bool seen_text = false; + string current_section = ""; + string current_block = ""; // meta, make, doc_has, or section name + + foreach (line; content.splitter("\n")) { + /+ ↓ comment. The first line of a .ssp declares the format version, and + it is the one comment that carries meaning: a reader checks the + major part and refuses what it does not know rather than loading + an unfamiliar artefact half populated in silence. + +/ + if (line.length > 0 && line[0] == '%') { + enum _banner = "% SiSU Document Abstraction v"; + enum _source = "% Source: "; + if (doc.format_version.length == 0 && line.startsWith(_banner)) { + doc.format_version = line[_banner.length .. $].strip; + } else if (doc.source_filename.length == 0 && line.startsWith(_source)) { + doc.source_filename = line[_source.length .. $].strip; + } + continue; + } + + /+ ↓ blank line - finalize current object +/ + if (line.length == 0 || line.strip.length == 0) { + if (in_object) { + commitObject(doc, current_section, current_obj); + current_obj = OcdaObject.init; + in_object = false; + seen_text = false; + } + continue; + } + + /+ ↓ section/block open +/ + if (line[0] == '@') { + auto brace_pos = line.indexOf('{'); + if (brace_pos > 0) { + string name = line[1 .. brace_pos].strip; + current_block = name; + if (!isPreambleBlock(name)) { + current_section = name; + /+ ↓ a block that is neither preamble nor a section this reader + knows: counted, so that --report-unknown can say so +/ + if (doc.sectionByName(name) is null) { + doc.unknown.block[name]++; + } + } + } + continue; + } + + /+ ↓ section/block close +/ + if (line[0] == '}') { + if (in_object) { + commitObject(doc, current_section, current_obj); + current_obj = OcdaObject.init; + in_object = false; + seen_text = false; + } + current_block = ""; + continue; + } + + /+ ↓ inside meta/make/doc_has blocks: key-value pairs +/ + if (isPreambleBlock(current_block)) { + string stripped = line.stripLeft; + auto colon_pos = stripped.indexOf(':'); + if (colon_pos > 0) { + string key = stripped[0 .. colon_pos].strip; + string value = (colon_pos + 1 < stripped.length) + ? stripped[colon_pos + 1 .. $].strip : ""; + if (current_block == "meta") { doc.metadata[key] = value; } + else if (current_block == "make") { doc.make[key] = value; } + else if (current_block == "source") { doc.source[key] = value; } + else { doc.doc_has[key] = value; } + } + continue; + } + + /+ ↓ object declaration: [N] type ... +/ + if (line[0] == '[') { + if (in_object) { + commitObject(doc, current_section, current_obj); + } + current_obj = OcdaObject.init; + current_obj.section = current_section; + in_object = true; + seen_text = false; + parseObjectDeclaration(line, current_obj); + continue; + } + + /+ ↓ property: .name: value +/ + if (line[0] == '.') { + if (in_object) { + parseProperty(line, current_obj, doc.unknown); + } + continue; + } + + /+ ↓ text content: | content +/ + if (line.length >= 1 && line[0] == '|') { + if (in_object) { + string text_content = (line.length > 2) ? line[2 .. $] : ""; + if (seen_text) { + current_obj.text ~= "\n" ~ text_content; + } else { + current_obj.text = text_content; + seen_text = true; + } + } + continue; + } + + /+ ↓ no known shape. Counted by its first character so that a reader + can be told the file held something this one did not expect + +/ + doc.unknown.line[line[0 .. 1].idup]++; + } + + /+ ↓ finalize last object +/ + if (in_object) { + commitObject(doc, current_section, current_obj); + } + + return doc; +} + +private void parseObjectDeclaration(string line, ref OcdaObject obj) { + /+ parse: [N] type :level identifier +/ + auto bracket_close = line.indexOf(']'); + if (bracket_close < 0) return; + try { + obj.ocn = line[1 .. bracket_close].strip.to!int; + } catch (ConvException) { + obj.ocn = 0; + } + string rest = (bracket_close + 1 < line.length) + ? line[bracket_close + 1 .. $].strip : ""; + if (rest.length == 0) return; + + auto parts = rest.split(" "); + if (parts.length == 0) return; + obj.is_a = parts[0]; + + if (obj.is_a == "heading" && parts.length >= 2) { + /+ parse :A, :B, :1, etc. +/ + string lev = parts[1]; + if (lev.length >= 2 && lev[0] == ':') { + obj.heading_level = lev[1 .. $]; + } + /+ optional identifier after level +/ + if (parts.length >= 3) { + obj.identifier = parts[2]; + } + } +} + +/+ ↓ the blocks that are document preamble rather than sections of objects +/ +private bool isPreambleBlock(string name) { + return name == "source" || name == "meta" || name == "make" || name == "doc_has"; +} + +private void parseProperty(string line, ref OcdaObject obj, ref OcdaUnknown unknown) { + /+ parse: .name: value +/ + auto colon_pos = line.indexOf(':'); + if (colon_pos < 1) return; + string name = line[1 .. colon_pos].strip; + string value = (colon_pos + 1 < line.length) + ? line[colon_pos + 1 .. $].strip : ""; + + switch (name) { + case "part": obj.part = value; break; + case "is_of_type": obj.is_of_type = value; break; + case "section": obj.own_section = value; break; + case "identifier": obj.identifier = value; break; + case "segment_html_is": obj.segment_html_is = value; break; + /+ ↓ the epub segments at heading levels 1 to 4 where the html + segments at level 4 alone, so the two are different files and + the abstraction records both +/ + case "segment_epub": obj.segment_epub = value; break; + case "segment_epub_is": obj.segment_epub_is = value; break; + case "table_aligns": obj.table_aligns = value; break; + case "stow_link": obj.stow_link ~= value; break; + case "anchor_tag": obj.anchor_tags ~= value; break; + case "parent": obj.parent_ocn = toIntSafe(value); break; + case "last_descendant": obj.last_descendant_ocn = toIntSafe(value); break; + case "children": obj.children = parseIntArray(value); break; + case "ancestors": obj.ancestors = parseIntArray(value); break; + case "dummy": obj.dummy_heading = (value == "true"); break; + case "ocn_off": obj.ocn_off = (value == "true"); break; + case "indent": + auto parts = value.split(" "); + if (parts.length >= 1) obj.indent_base = toIntSafe(parts[0]); + if (parts.length >= 2) obj.indent_hang = toIntSafe(parts[1]); + break; + case "bullet": obj.bullet = (value == "true"); break; + case "lang": obj.lang = value; break; + case "has": + foreach (flag; value.split(" ")) { + switch (flag) { + case "links": obj.has_links = true; break; + case "notes_reg": obj.has_notes_reg = true; break; + case "notes_star": obj.has_notes_star = true; break; + case "images": obj.has_images = true; break; + default: break; + } + } + break; + case "segment": obj.segment = value; break; + case "segment_prev": obj.segment_prev = value; break; + case "segment_next": obj.segment_next = value; break; + case "anchor": obj.anchor = value; break; + case "heading_lev_anchor": obj.heading_lev_anchor = value; break; + case "table_cols": obj.table_cols = toIntSafe(value); break; + case "table_widths": obj.table_widths = value; break; + case "table_header": obj.table_header = (value == "true"); break; + case "code_syntax": obj.code_syntax = value; break; + case "code_linenumbers": obj.code_linenumbers = (value == "true"); break; + case "heading_ancestors_text": obj.heading_ancestors_text = value; break; + case "sha256": obj.sha256 = value; break; + case "image": obj.images ~= parseImageRecord(value); break; + /+ ↓ a property this reader has no use for, or has never heard of. + Ignored, which is the conforming behaviour within a major + version, but counted rather than passed over in silence + +/ + default: unknown.property[name]++; break; + } +} + +private OcdaImage parseImageRecord(string value) { + /+ parse: <filename> sha256:<HEX> bytes:<n> [key:value ...] + filename first, remaining fields order-independent; unrecognised + fields are kept rather than discarded +/ + OcdaImage img; + bool first = true; + foreach (field; value.split(" ")) { + if (field.length == 0) continue; + if (first) { + img.name = field; + first = false; + continue; + } + auto colon_pos = field.indexOf(':'); + if (colon_pos < 1) continue; + string key = field[0 .. colon_pos]; + string val = (colon_pos + 1 < field.length) ? field[colon_pos + 1 .. $] : ""; + switch (key) { + case "sha256": img.sha256 = val; break; + case "bytes": img.bytes = toUlongSafe(val); break; + case "px": + auto dims = val.split("x"); + if (dims.length == 2) { + img.width = toIntSafe(dims[0]); + img.height = toIntSafe(dims[1]); + } + break; + case "missing": img.missing = (val == "true"); break; + default: img.fields[key] = val; break; + } + } + return img; +} + +/+ ↓ two values the text form leaves out because they can be worked out. + . + The .ssp emits a property only when it carries information, so + .identifier is absent when it is simply the ocn, and .anchor is absent + when it is the segment name. The .ocda.db, being columns rather than + lines, stores both unconditionally. So a loader that takes the text + form literally gives a *different model* from the one the database + gives, and the difference is not small: in the reference collection + the identifier is omitted on all but a handful of objects. + . + The model is the thing both serialisations describe, so the loader + fills them in. Found by dumping both models and diffing them, which no + amount of comparing section counts would have shown. ++/ +private void deriveOmitted(ref OcdaObject obj) { + import std.conv : to; + if (obj.identifier.length == 0 && obj.ocn != 0) { + obj.identifier = obj.ocn.to!string; + } + if (obj.anchor.length == 0 && obj.segment.length > 0) { + obj.anchor = obj.segment; + } +} + +private void commitObject(ref OcdaDocument doc, string section, ref OcdaObject obj) { + deriveOmitted(obj); + auto sec = doc.sectionByName(section); + if (sec !is null) { + *sec ~= obj; + } +} + +private int toIntSafe(string s) { + try { return s.strip.to!int; } + catch (ConvException) { return 0; } +} + +private ulong toUlongSafe(string s) { + try { return s.strip.to!ulong; } + catch (ConvException) { return 0; } +} + +private int[] parseIntArray(string s) { + int[] result; + foreach (part; s.split(" ")) { + auto v = toIntSafe(part); + result ~= v; + } + return result; +} |
