diff options
| -rw-r--r-- | org/in_abstraction_artefacts.org | 14 | ||||
| -rw-r--r-- | org/ocda.org | 28 | ||||
| -rw-r--r-- | org/ocda_functions.org | 1 | ||||
| -rw-r--r-- | org/out_sqlite.org | 81 | ||||
| -rw-r--r-- | org/out_xmls.org | 173 | ||||
| -rw-r--r-- | org/out_xmls_css.org | 36 | ||||
| -rw-r--r-- | org/tests_for_document_abstraction_shell_scripts.org | 16 | ||||
| -rw-r--r-- | src/sisudoc/ocda/abstraction/doc_has.d | 14 | ||||
| -rw-r--r-- | src/sisudoc/ocda/meta/metadoc_from_src.d | 28 | ||||
| -rw-r--r-- | src/sisudoc/ocda/meta/metadoc_from_src_functions.d | 1 | ||||
| -rw-r--r-- | src/sisudoc/outputs/io_out/epub3.d | 68 | ||||
| -rw-r--r-- | src/sisudoc/outputs/io_out/sqlite_collection_db.d | 81 | ||||
| -rw-r--r-- | src/sisudoc/outputs/io_out/xmls.d | 91 | ||||
| -rw-r--r-- | src/sisudoc/outputs/io_out/xmls_css.d | 108 | ||||
| -rw-r--r-- | test/reference/abstraction/content.cory_doctorow.en.ssp | 28 | ||||
| -rw-r--r-- | test/reference/abstraction/live-manual.es.ssp | 2 | ||||
| -rw-r--r-- | test/reference/abstraction/the_public_domain.james_boyle.en.ssp | 20 | ||||
| -rwxr-xr-x | test/test-epub-validity.sh | 16 |
18 files changed, 623 insertions, 183 deletions
diff --git a/org/in_abstraction_artefacts.org b/org/in_abstraction_artefacts.org index 863134c..2852a94 100644 --- a/org/in_abstraction_artefacts.org +++ b/org/in_abstraction_artefacts.org @@ -1436,8 +1436,18 @@ template spineDocHasFromAbstraction() { _tag_assoc[obj.metainfo.identifier]["seg_lv4"] = obj.tags.html_segment_anchor_tag_is; } - _tag_assoc[obj.metainfo.identifier]["seg_lv1to4"] - = obj.tags.epub_segment_anchor_tag_is; + /+ ↓ An object that is not written into any segment still carries an + identifier, and can share it: a poem block and its verses have one + ocn between them, the verses are written and the block itself is not. + The block comes second, so an unguarded assignment replaced a good + segment name with an empty one, and the link came out as + ".xhtml#297". seg_lv4 above is guarded already, which is why this + showed in the epub and not in the html. + +/ + if (obj.tags.epub_segment_anchor_tag_is.length > 0) { + _tag_assoc[obj.metainfo.identifier]["seg_lv1to4"] + = obj.tags.epub_segment_anchor_tag_is; + } } } _out.imagelist = _images.sort.uniq.array; diff --git a/org/ocda.org b/org/ocda.org index ee490f4..ce03d32 100644 --- a/org/ocda.org +++ b/org/ocda.org @@ -185,6 +185,7 @@ scope(exit) { reset_note_numbers = true; lev_anchor_tag = ""; anchor_tag = ""; + _heading_anchor_tags_seen = _heading_anchor_tags_seen.init; } mixin spineNode; int[string] node_para_int_ = node_metadata_para_int; @@ -722,6 +723,18 @@ _loopMarkupSrcByLineStruct loopMarkupSrcByLine( = obj_im.obj_inline_markup_and_anchor_tags_and_misc(an_object, an_object_key, conf_make_meta, ((_new_doc) ? Yes._new_doc : No._new_doc)); an_object["substantive"] = substantive_object_and_anchor_tags_struct.obj_txt; anchor_tag = substantive_object_and_anchor_tags_struct.anchor_tag; + /+ ↓ an anchor tag names one heading. Markup can give the + same name to several ("2~x- 1.", "2~x- 2." ...), and + an id has to be unique within a document, so a repeat + takes the ocn as a suffix. The first keeps the name + the author wrote, so a link to it still arrives. + +/ + if (!(anchor_tag.empty)) { + if (anchor_tag in _heading_anchor_tags_seen) { + anchor_tag = anchor_tag ~ "-" ~ obj_cite_digits.object_number.to!string; + } + _heading_anchor_tags_seen[anchor_tag] = true; + } if (_new_doc) { cnt1 = 1; cnt2 = 1; @@ -1116,8 +1129,18 @@ if (the_document_body_section.length > 1) { // writeln("body"); tag_assoc[(obj.metainfo.identifier)]["seg_lv4"] = obj.tags.html_segment_anchor_tag_is; } - tag_assoc[(obj.metainfo.identifier)]["seg_lv1to4"] - = obj.tags.epub_segment_anchor_tag_is; + /+ ↓ An object that is not written into any segment still carries an + identifier, and can share it: a poem block and its verses have one + ocn between them, the verses are written and the block itself is not. + The block comes second, so an unguarded assignment replaced a good + segment name with an empty one, and the link came out as + ".xhtml#297". seg_lv4 above is guarded already, which is why this + showed in the epub and not in the html. + +/ + if (!(obj.tags.epub_segment_anchor_tag_is.empty)) { + tag_assoc[(obj.metainfo.identifier)]["seg_lv1to4"] + = obj.tags.epub_segment_anchor_tag_is; + } } if (obj.metainfo.is_a == "heading") { debug(dom) { writeln(obj.text); } @@ -1700,6 +1723,7 @@ html_segnames_ptr_cntr = 0; content_non_header = "8"; lev_anchor_tag = ""; anchor_tag = ""; +_heading_anchor_tags_seen = _heading_anchor_tags_seen.init; // identify parts /+ ↓ what the document has, as plain data. ST_DocHas is in metadoc_object_setter so that it can also be built from a loaded diff --git a/org/ocda_functions.org b/org/ocda_functions.org index ca8a7be..33c94e4 100644 --- a/org/ocda_functions.org +++ b/org/ocda_functions.org @@ -59,6 +59,7 @@ string[] anchor_tags; string anchor_tag; string anchor_tag_; string[string] tag_in_seg; +bool[string] _heading_anchor_tags_seen; string lev_anchor_tag; string[string][string] tag_assoc; string[] lv0to3_tags; diff --git a/org/out_sqlite.org b/org/out_sqlite.org index 2895b72..a9f1065 100644 --- a/org/out_sqlite.org +++ b/org/out_sqlite.org @@ -1268,35 +1268,58 @@ string html_table(M,O)( string[] _table_cols; string _table; string _tablenote; + bool _in_head = false; + bool _in_body = false; foreach(row_idx, row; _table_rows) { _table_cols = row.split(rgx.table_delimiter_col); - _table ~= "<tr>"; - foreach(col_idx, cell; _table_cols) { - if ((_table_cols.length == 1) - && (_table_rows.length <= row_idx+2)) { // check row_idx+2 (rather than == ++row_idx) - _tablenote ~= cell; - } else { - string _col_is = (row_idx == 0 && obj.table.heading) ? "th" : "td"; - string _align = ("style=\"text-align:" - ~ ((obj.table.column_aligns[col_idx] == "l") - ? "left\"" : "right\"")); - _table ~= "<" - ~ _col_is - ~ " width=\"" - ~ obj.table.column_widths[col_idx].to!string - ~ "%\" " - ~ _align - ~ ">"; - _table ~= cell; - _table ~= "</" - ~ _col_is - ~ ">"; - } - } - _table ~= "</tr>"; + if ((_table_cols.length == 1) + && (_table_rows.length <= row_idx+2)) { // check row_idx+2 (rather than == ++row_idx) + _tablenote ~= _table_cols[0]; + continue; + } + /+ ↓ a heading row goes in <thead>, the rest in <tbody> +/ + if (row_idx == 0 && obj.table.heading) { + _table ~= "<thead>"; + _in_head = true; + } else if (!_in_body) { + if (_in_head) { _table ~= "</thead>"; _in_head = false; } + _table ~= "<tbody>"; + _in_body = true; + } + _table ~= "<tr>"; + foreach(col_idx, cell; _table_cols) { + bool _is_th = (row_idx == 0 && obj.table.heading); + string _col_is = _is_th ? "th" : "td"; + string _class = (col_idx < obj.table.column_aligns.length + && obj.table.column_aligns[col_idx] == "l") ? "left" : "right"; + _table ~= "<" + ~ _col_is + ~ (_is_th ? " scope=\"col\"" : "") + ~ " class=\"" + ~ _class + ~ "\">"; + _table ~= cell; + _table ~= "</" + ~ _col_is + ~ ">"; } + _table ~= "</tr>"; + } + if (_in_head) { _table ~= "</thead>"; } + else if (_in_body) { _table ~= "</tbody>"; } + /+ ↓ column widths as a <colgroup>, not a width attribute on every cell +/ + string _colgroup; + if (obj.table.column_widths.length > 0) { + string _cols; + foreach(w; obj.table.column_widths) { + _cols ~= (w > 0) + ? "<col style=\"width:" ~ w.to!string ~ "%\" />" + : "<col />"; + } + _colgroup = "<colgroup>" ~ _cols ~ "</colgroup>"; + } Tuple!(string, string) t = tuple( - _table, + (_colgroup ~ _table), _tablenote, ); return t; @@ -1305,15 +1328,15 @@ string html_table(M,O)( Tuple!(string, string) t = _tablarize(obj, _txt); _txt = t[0]; string _note = t[1]; - string o = format(q"┃<p class="%s"> - <table summary="normal text css" width="95%%" border="0" cellpadding="2" align="center"> + string o = format(q"┃<div class="%s"> + <table class="table"> %s </table> %s - </p>┃", + </div>┃", obj.metainfo.is_a, _txt, - _note + (_note.strip.empty) ? "" : ("<p class=\"tablenote\">" ~ _note.strip ~ "</p>") ); return o; } diff --git a/org/out_xmls.org b/org/out_xmls.org index 33dfa5d..4d1c4a7 100644 --- a/org/out_xmls.org +++ b/org/out_xmls.org @@ -41,6 +41,7 @@ template outputXHTMLs() { <<xhtml_format_objects_special_characters_date>> <<xhtml_format_objects_breaks_indents_bullets>> <<xhtml_format_objects_font_face>> + <<xhtml_format_objects_xml_heading_element>> <<xhtml_format_objects_xml_anchor_tags>> <<xhtml_format_objects_header_metadata>> <<xhtml_format_objects_site_info_button>> @@ -301,6 +302,23 @@ string font_face(string _txt) { **** anchor tags +#+NAME: xhtml_format_objects_xml_heading_element +#+BEGIN_SRC d +/+ ↓ the heading element for a markup level. + Markup goes to level 7; HTML stops at h6, and an <h7> is simply + not an element, so the deepest three markup levels share h6 and + are told apart by the "heading" class and their ocn. Level 0 is + the document title, which is h1 in a segment of its own. ++/ +int _heading_element_level(O)(O obj, string _xml_type) { + int _lev = obj.metainfo.heading_lev_markup.to!int; + if (_xml_type == "epub" && _lev == 0) { return 1; } + return (_lev > 6) ? 6 : _lev; +} +#+END_SRC + +**** anchor tags + #+NAME: xhtml_format_objects_xml_anchor_tags #+BEGIN_SRC d string _xhtml_anchor_tags(O)(O obj) { @@ -639,13 +657,13 @@ string tail(M)(M doc_matters) { string o; o = format(q"┃<hr /> <div class="rights"> - <p class="small" id="copyright"> + <p class="small" id="doc_footer_copyright"> <b>Copyright:</b> %s </p> </div> %s <div class="rights"> - <p class="small" id="rights"> + <p class="small" id="doc_footer_rights"> %s </p> </div> @@ -737,7 +755,9 @@ string inline_links(O,M)( if (_xml_type == "seg" || _xml_type == "epub") { seg_lvs = (_xml_type == "epub") ? "seg_lv1to4" : "seg_lv4"; foreach (m; _txt.match(rgx.inline_link_hash)) { - if (m.captures["hash"] in doc_matters.has.tag_associations) { + if ((m.captures["hash"] in doc_matters.has.tag_associations) + && (seg_lvs in doc_matters.has.tag_associations[(m.captures["hash"])]) + ) { if ( m.captures["hash"] == doc_matters.has.tag_associations[(m.captures["hash"])][seg_lvs] @@ -1132,15 +1152,13 @@ string heading(O,M)( (doc_matters.opt.action.ocn_off) ? "" : ((obj.metainfo.object_number.empty) ? "" : obj.metainfo.identifier), - ((_xml_type == "epub" && obj.metainfo.heading_lev_markup == 0) ? 1 - : obj.metainfo.heading_lev_markup), + _heading_element_level(obj, _xml_type), obj.metainfo.is_a, obj.metainfo.identifier, tags, heading_lev_anchor_tag, _txt, - ((_xml_type == "epub" && obj.metainfo.heading_lev_markup == 0) ? 1 - : obj.metainfo.heading_lev_markup), + _heading_element_level(obj, _xml_type), ); } else { o ~= format(q"┃%s @@ -1150,14 +1168,12 @@ string heading(O,M)( </h%s> </div>┃", _horizontal_rule, - ((_xml_type == "epub" && obj.metainfo.heading_lev_markup == 0) ? 1 - : obj.metainfo.heading_lev_markup), + _heading_element_level(obj, _xml_type), obj.metainfo.is_a, tags, heading_lev_anchor_tag, _txt, - ((_xml_type == "epub" && obj.metainfo.heading_lev_markup == 0) ? 1 - : obj.metainfo.heading_lev_markup), + _heading_element_level(obj, _xml_type), ); } return o; @@ -1706,6 +1722,17 @@ align="left|right|center" #+NAME: xhtml_format_objects_tablarize #+BEGIN_SRC d +/+ ↓ column widths as a <colgroup>, not a width attribute on every cell +/ +string _table_colgroup(O)(const O obj) { + if (obj.table.column_widths.length == 0) { return ""; } + string _cols; + foreach(w; obj.table.column_widths) { + _cols ~= (w > 0) + ? "<col style=\"width:" ~ w.to!string ~ "%\" />" + : "<col />"; + } + return "<colgroup>" ~ _cols ~ "</colgroup>"; +} Tuple!(string, string) tablarize(O)( string _txt, const O obj, @@ -1714,27 +1741,42 @@ Tuple!(string, string) tablarize(O)( string[] _table_cols; string _table; string _tablenote; + bool _in_head = false; + bool _in_body = false; foreach(row_idx, row; _table_rows) { _table_cols = row.split(rgx.table_delimiter_col); + if ((_table_cols.length == 1) + && (_table_rows.length <= row_idx+2)) { + _tablenote ~= _table_cols[0]; + continue; + } + /+ ↓ a heading row goes in <thead>, the rest in <tbody> +/ + if (row_idx == 0 && obj.table.heading) { + _table ~= "<thead>"; + _in_head = true; + } else if (!_in_body) { + if (_in_head) { _table ~= "</thead>"; _in_head = false; } + _table ~= "<tbody>"; + _in_body = true; + } _table ~= "<tr>"; foreach(col_idx, cell; _table_cols) { - if ((_table_cols.length == 1) - && (_table_rows.length <= row_idx+2)) { - _tablenote ~= cell; - } else { - string _col_is = (row_idx == 0 && obj.table.heading) ? "th" : "td"; - string _align = ("style=\"text-align:" - ~ ((obj.table.column_aligns[col_idx] == "l") - ? "left\"" : "right\"")); - _table ~= "<" ~ _col_is ~ " width=\"" ~ obj.table.column_widths[col_idx].to!string ~ "%\" " ~ _align ~ ">"; - _table ~= cell; - _table ~= "</" ~ _col_is ~ ">"; - } + bool _is_th = (row_idx == 0 && obj.table.heading); + string _col_is = _is_th ? "th" : "td"; + string _class = (col_idx < obj.table.column_aligns.length + && obj.table.column_aligns[col_idx] == "l") ? "left" : "right"; + _table ~= "<" ~ _col_is + ~ (_is_th ? " scope=\"col\"" : "") + ~ " class=\"" ~ _class ~ "\">"; + _table ~= cell; + _table ~= "</" ~ _col_is ~ ">"; } _table ~= "</tr>"; } + if (_in_head) { _table ~= "</thead>"; } + else if (_in_body) { _table ~= "</tbody>"; } Tuple!(string, string) t = tuple( - _table, + (_table_colgroup(obj) ~ _table), _tablenote, ); return t; @@ -1762,12 +1804,12 @@ string table(O,M)( string o; o = format(q"┃ <div class="substance"> <label class="ocn"><a href="#%s" class="lnkocn">%s</a></label> - <p class="%s" id="%s">%s - <table summary="normal text css" width="95%%" border="0" cellpadding="2" align="center"> + <div class="%s" id="%s">%s + <table class="table"> %s </table> %s - </p> + </div> </div>┃", obj.metainfo.object_number, (doc_matters.opt.action.ocn_off) ? "" : ((obj.metainfo.object_number.empty) ? "" : obj.metainfo.identifier), @@ -1775,7 +1817,7 @@ string table(O,M)( obj.metainfo.object_number, tags, _txt, - _note + (_note.strip.empty) ? "" : ("<p class=\"tablenote\">" ~ _note.strip ~ "</p>") ); return o; } @@ -2507,6 +2549,7 @@ template outputEPub3() { static auto rgx = RgxO(); static auto rgx_xhtml = RgxXHTML(); <<xhtml_format_objects_special_characters_text>> + <<output_epub3_manifest_id>> <<output_epub3_last_modified_time>> <<output_epub3_fixed_mimetypes>> <<output_epub3_fixed_container_xml>> @@ -2528,6 +2571,51 @@ template outputEPub3() { #+END_SRC ** special (epub) files :format: + + +#+NAME: output_epub3_manifest_id +#+BEGIN_SRC d +/+ ↓ a manifest item id, which has to be an XML name. + An XML name may not begin with a digit, and a file quite happily + may: "2bits_02_01-100.png" gave id="2bits_02_01-100", which is not + a name. A prefix settles the first character, and anything else a + filename allows and a name does not becomes an underscore. +/ +string _manifest_id(string _prefix, string _name) { + string _id; + foreach (c; _name) { + _id ~= ((c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z') + || (c >= '0' && c <= '9') || c == '_' || c == '-' || c == '.') + ? c : '_'; + } + return _prefix ~ "_" ~ _id; +} +/+ ↓ the media type of an image, which is not its file extension. + There is no "image/jpg"; a manifest that claims one is declaring a + foreign resource, and EPUB then demands a fallback for it. The + core image types are these, and anything else genuinely is + foreign. +/ +string _image_media_type(string _ext) { + switch (_ext.toLower) { + case "jpg": case "jpeg": return "image/jpeg"; + case "png": return "image/png"; + case "gif": return "image/gif"; + case "svg": case "svgz": return "image/svg+xml"; + case "webp": return "image/webp"; + default: return "image/" ~ _ext.toLower; + } +} +/+ ↓ the publication identifier, as a real RFC 4122 UUID. + Version 5, name based: the name is the document's own uid, so the + identifier is stable across rebuilds and distinct per document, + which is what dc:identifier is for. A random v4 would be neither. + The namespace is v5 of "sisudoc.org" under the DNS namespace. +/ +string _epub_publication_uuid(string _doc_uid) { + import std.uuid : sha1UUID, dnsNamespace; + auto _ns = sha1UUID("sisudoc.org", dnsNamespace); + return sha1UUID(_doc_uid, _ns).toString; +} +#+END_SRC + *** time #+NAME: output_epub3_last_modified_time @@ -2590,7 +2678,7 @@ xmlns="urn:oasis:names:tc:opendocument:xmlns:container"> #+NAME: epub3_package_version #+BEGIN_SRC d -<package version="3.0" xmlns="http://www.idpf.org/2007/opf" unique-identifier="bookid" prefix="rendition: http://www.idpf.org/vocab/rendition/#"> +<package version="3.0" xmlns="http://www.idpf.org/2007/opf" unique-identifier="bookid" xml:lang="%s"> #+END_SRC #+NAME: output_epub3_constructs_oebps_content @@ -2599,11 +2687,10 @@ xmlns="urn:oasis:names:tc:opendocument:xmlns:container"> string epub3_oebps_content(D,P)(D doc, P parts) { auto xhtml_format = outputXHTMLs(); auto pth_epub3 = spinePathsEPUB!()(doc.matters.output_path, doc.matters.src.language); - string _uuid = "18275d951861c77f78acd05672c9906924c59f18a2e0ba06dad95959693e9bd8"; // TODO sort uuid in doc.matters! + string _uuid = _epub_publication_uuid(doc.matters.src.doc_uid_out); string content = format(q"┃<?xml version="1.0" encoding="utf-8"?> <<epub3_package_version>> <metadata - xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dc="http://purl.org/dc/elements/1.1/"> <dc:identifier id="bookid">urn:uuid:%s</dc:identifier> @@ -2620,6 +2707,7 @@ string epub3_oebps_content(D,P)(D doc, P parts) { <item id="css" href="%s" media-type="text/css"/> <item id="nav" href="toc_nav.xhtml" media-type="application/xhtml+xml" properties="nav" /> ┃", + doc.matters.src.language, _uuid, xhtml_format.special_characters_plain(doc.matters.conf_make_meta.meta.title_main), (doc.matters.conf_make_meta.meta.title_sub.empty) ? "" : format( @@ -2639,14 +2727,13 @@ string epub3_oebps_content(D,P)(D doc, P parts) { (pth_epub3.fn_oebps_css).chompPrefix("OEBPS/"), ); content ~= parts["manifest_documents"]; - // TODO sort jpg & png foreach (image; doc.matters.srcs.image_list) { - content ~= format(q"┃ <item id="%s" href="%s/%s" media-type="image/%s" /> + content ~= format(q"┃ <item id="%s" href="%s/%s" media-type="%s" /> ┃", - image.baseName.stripExtension, + _manifest_id("img", image.baseName.stripExtension), (pth_epub3.doc_oebps_image).chompPrefix("OEBPS/"), image, - image.extension.chompPrefix("."), + _image_media_type(image.extension.chompPrefix(".")), ); } content ~= " " ~ "</manifest>" ~ "\n "; @@ -2753,8 +2840,14 @@ string epub3_oebps_toc_nav_xhtml(D)(D doc) { _new_title_set = true; } else { _new_title_set = false; + /+ ↓ a fragment only where there is one to reach. + A heading of level 4 or less is the top of its own + file, so the file is the target. A heading below + that sits inside a file and carries id="<ocn>", so + that is the fragment. An object with no ocn has no + id, and "#0" was pointing at nothing. +/ string _hashtag = ""; - if ((obj.metainfo.heading_lev_markup <= 4) && (obj.metainfo.ocn == 0)) { + if ((obj.metainfo.heading_lev_markup > 4) && (obj.metainfo.ocn > 0)) { _hashtag = "#" ~ obj.metainfo.ocn.to!string; } string _href = "<a href=\"" @@ -3132,15 +3225,15 @@ if (obj.metainfo.is_a == "heading" ) { _segment_files_seen[obj.tags.segment_anchor_tag_epub] = true; oepbs_content_parts["manifest_documents"] ~= - format(q"┃<item id="%s.xhtml" href="%s.xhtml" media-type="application/xhtml+xml" /> + format(q"┃<item id="%s" href="%s.xhtml" media-type="application/xhtml+xml" /> ┃", - obj.tags.segment_anchor_tag_epub, + _manifest_id("seg", obj.tags.segment_anchor_tag_epub), obj.tags.segment_anchor_tag_epub, ); oepbs_content_parts["spine"] ~= - format(q"┃<itemref idref="%s.xhtml" linear="yes" /> + format(q"┃<itemref idref="%s" linear="yes" /> ┃", - obj.tags.segment_anchor_tag_epub, + _manifest_id("seg", obj.tags.segment_anchor_tag_epub), ); #+END_SRC diff --git a/org/out_xmls_css.org b/org/out_xmls_css.org index 3ae8e86..ae361c0 100644 --- a/org/out_xmls_css.org +++ b/org/out_xmls_css.org @@ -643,6 +643,24 @@ table { margin-right : 2em; background-color : inherit; } +div.table { + margin : 1em 0; + overflow-x : auto; +} +table.table { + display : table; + width : 95%%; + margin : 0 auto; + border-collapse : collapse; + background-color : inherit; +} +table.table th, table.table td { + padding : 2px; + vertical-align : top; +} +p.tablenote { + margin : 0.5em 0 0 0; +} tr { } th,td { vertical-align : top; @@ -1574,6 +1592,24 @@ table { margin-right : 2em; background-color : inherit; } +div.table { + margin : 1em 0; + overflow-x : auto; +} +table.table { + display : table; + width : 95%%; + margin : 0 auto; + border-collapse : collapse; + background-color : inherit; +} +table.table th, table.table td { + padding : 2px; + vertical-align : top; +} +p.tablenote { + margin : 0.5em 0 0 0; +} tr { } th,td { vertical-align : top; diff --git a/org/tests_for_document_abstraction_shell_scripts.org b/org/tests_for_document_abstraction_shell_scripts.org index a70a5f4..369a7f6 100644 --- a/org/tests_for_document_abstraction_shell_scripts.org +++ b/org/tests_for_document_abstraction_shell_scripts.org @@ -1278,13 +1278,17 @@ SPINE_DIR="$(cd "$SCRIPT_DIR/.." && pwd)" # markup and left an unbalanced </a> behind - was a url boundary defect in # the abstraction, and is fixed. # -# The errors that remain are, in order of how many: -# the table writer's obsolete presentational attributes, width on every -# cell and summary/border/cellpadding/align on the table; the navigation -# document linking to "#0", a fragment that is never defined; duplicate -# ids; a table inside a <p>; an opf id containing a colon. +# No error is allowed either, and none is outstanding. Both numbers being +# zero is the point: anything at all that epubcheck calls an error is a +# regression, and there is no list to add to. +# +# Two warnings remain and are not counted here. Both are NAV-011 in the +# same shape, in two documents: the navigation document lists one file +# twice, and the repeat is behind the previous entry in spine order. It +# comes from how the endnotes part and section headings are ordered, not +# from the navigation writer. FATALS_ALLOWED=${SpineEpubFatalsAllowed:-0} -ERRORS_ALLOWED=${SpineEpubErrorsAllowed:-1312} +ERRORS_ALLOWED=${SpineEpubErrorsAllowed:-0} if [ -z "$SpinePOD" ]; then echo "ERROR: \$SpinePOD is not set." >&2 diff --git a/src/sisudoc/ocda/abstraction/doc_has.d b/src/sisudoc/ocda/abstraction/doc_has.d index ecdef25..4ecf018 100644 --- a/src/sisudoc/ocda/abstraction/doc_has.d +++ b/src/sisudoc/ocda/abstraction/doc_has.d @@ -264,8 +264,18 @@ template spineDocHasFromAbstraction() { _tag_assoc[obj.metainfo.identifier]["seg_lv4"] = obj.tags.html_segment_anchor_tag_is; } - _tag_assoc[obj.metainfo.identifier]["seg_lv1to4"] - = obj.tags.epub_segment_anchor_tag_is; + /+ ↓ An object that is not written into any segment still carries an + identifier, and can share it: a poem block and its verses have one + ocn between them, the verses are written and the block itself is not. + The block comes second, so an unguarded assignment replaced a good + segment name with an empty one, and the link came out as + ".xhtml#297". seg_lv4 above is guarded already, which is why this + showed in the epub and not in the html. + +/ + if (obj.tags.epub_segment_anchor_tag_is.length > 0) { + _tag_assoc[obj.metainfo.identifier]["seg_lv1to4"] + = obj.tags.epub_segment_anchor_tag_is; + } } } _out.imagelist = _images.sort.uniq.array; diff --git a/src/sisudoc/ocda/meta/metadoc_from_src.d b/src/sisudoc/ocda/meta/metadoc_from_src.d index fb30a94..c856de3 100644 --- a/src/sisudoc/ocda/meta/metadoc_from_src.d +++ b/src/sisudoc/ocda/meta/metadoc_from_src.d @@ -95,6 +95,7 @@ template docAbstraction() { reset_note_numbers = true; lev_anchor_tag = ""; anchor_tag = ""; + _heading_anchor_tags_seen = _heading_anchor_tags_seen.init; } mixin spineNode; int[string] node_para_int_ = node_metadata_para_int; @@ -618,6 +619,18 @@ template docAbstraction() { = obj_im.obj_inline_markup_and_anchor_tags_and_misc(an_object, an_object_key, conf_make_meta, ((_new_doc) ? Yes._new_doc : No._new_doc)); an_object["substantive"] = substantive_object_and_anchor_tags_struct.obj_txt; anchor_tag = substantive_object_and_anchor_tags_struct.anchor_tag; + /+ ↓ an anchor tag names one heading. Markup can give the + same name to several ("2~x- 1.", "2~x- 2." ...), and + an id has to be unique within a document, so a repeat + takes the ocn as a suffix. The first keeps the name + the author wrote, so a link to it still arrives. + +/ + if (!(anchor_tag.empty)) { + if (anchor_tag in _heading_anchor_tags_seen) { + anchor_tag = anchor_tag ~ "-" ~ obj_cite_digits.object_number.to!string; + } + _heading_anchor_tags_seen[anchor_tag] = true; + } if (_new_doc) { cnt1 = 1; cnt2 = 1; @@ -1005,8 +1018,18 @@ template docAbstraction() { tag_assoc[(obj.metainfo.identifier)]["seg_lv4"] = obj.tags.html_segment_anchor_tag_is; } - tag_assoc[(obj.metainfo.identifier)]["seg_lv1to4"] - = obj.tags.epub_segment_anchor_tag_is; + /+ ↓ An object that is not written into any segment still carries an + identifier, and can share it: a poem block and its verses have one + ocn between them, the verses are written and the block itself is not. + The block comes second, so an unguarded assignment replaced a good + segment name with an empty one, and the link came out as + ".xhtml#297". seg_lv4 above is guarded already, which is why this + showed in the epub and not in the html. + +/ + if (!(obj.tags.epub_segment_anchor_tag_is.empty)) { + tag_assoc[(obj.metainfo.identifier)]["seg_lv1to4"] + = obj.tags.epub_segment_anchor_tag_is; + } } if (obj.metainfo.is_a == "heading") { debug(dom) { writeln(obj.text); } @@ -1582,6 +1605,7 @@ template docAbstraction() { content_non_header = "8"; lev_anchor_tag = ""; anchor_tag = ""; + _heading_anchor_tags_seen = _heading_anchor_tags_seen.init; // identify parts /+ ↓ what the document has, as plain data. ST_DocHas is in metadoc_object_setter so that it can also be built from a loaded diff --git a/src/sisudoc/ocda/meta/metadoc_from_src_functions.d b/src/sisudoc/ocda/meta/metadoc_from_src_functions.d index 77770f4..08ee22c 100644 --- a/src/sisudoc/ocda/meta/metadoc_from_src_functions.d +++ b/src/sisudoc/ocda/meta/metadoc_from_src_functions.d @@ -66,6 +66,7 @@ template docAbstractionFunctions() { string anchor_tag; string anchor_tag_; string[string] tag_in_seg; + bool[string] _heading_anchor_tags_seen; string lev_anchor_tag; string[string][string] tag_assoc; string[] lv0to3_tags; diff --git a/src/sisudoc/outputs/io_out/epub3.d b/src/sisudoc/outputs/io_out/epub3.d index b00165d..420c536 100644 --- a/src/sisudoc/outputs/io_out/epub3.d +++ b/src/sisudoc/outputs/io_out/epub3.d @@ -77,6 +77,45 @@ template outputEPub3() { .replaceAll(rgx.nbsp_char, " "); return _txt; } + /+ ↓ a manifest item id, which has to be an XML name. + An XML name may not begin with a digit, and a file quite happily + may: "2bits_02_01-100.png" gave id="2bits_02_01-100", which is not + a name. A prefix settles the first character, and anything else a + filename allows and a name does not becomes an underscore. +/ + string _manifest_id(string _prefix, string _name) { + string _id; + foreach (c; _name) { + _id ~= ((c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z') + || (c >= '0' && c <= '9') || c == '_' || c == '-' || c == '.') + ? c : '_'; + } + return _prefix ~ "_" ~ _id; + } + /+ ↓ the media type of an image, which is not its file extension. + There is no "image/jpg"; a manifest that claims one is declaring a + foreign resource, and EPUB then demands a fallback for it. The + core image types are these, and anything else genuinely is + foreign. +/ + string _image_media_type(string _ext) { + switch (_ext.toLower) { + case "jpg": case "jpeg": return "image/jpeg"; + case "png": return "image/png"; + case "gif": return "image/gif"; + case "svg": case "svgz": return "image/svg+xml"; + case "webp": return "image/webp"; + default: return "image/" ~ _ext.toLower; + } + } + /+ ↓ the publication identifier, as a real RFC 4122 UUID. + Version 5, name based: the name is the document's own uid, so the + identifier is stable across rebuilds and distinct per document, + which is what dc:identifier is for. A random v4 would be neither. + The namespace is v5 of "sisudoc.org" under the DNS namespace. +/ + string _epub_publication_uuid(string _doc_uid) { + import std.uuid : sha1UUID, dnsNamespace; + auto _ns = sha1UUID("sisudoc.org", dnsNamespace); + return sha1UUID(_doc_uid, _ns).toString; + } /+ ↓ the last modified time, as EPUB3 requires it: exactly one dcterms:modified on the package, in UTC to the second, CCYY-MM-DDThh:mm:ssZ +/ @@ -105,11 +144,10 @@ template outputEPub3() { string epub3_oebps_content(D,P)(D doc, P parts) { auto xhtml_format = outputXHTMLs(); auto pth_epub3 = spinePathsEPUB!()(doc.matters.output_path, doc.matters.src.language); - string _uuid = "18275d951861c77f78acd05672c9906924c59f18a2e0ba06dad95959693e9bd8"; // TODO sort uuid in doc.matters! + string _uuid = _epub_publication_uuid(doc.matters.src.doc_uid_out); string content = format(q"┃<?xml version="1.0" encoding="utf-8"?> - <package version="3.0" xmlns="http://www.idpf.org/2007/opf" unique-identifier="bookid" prefix="rendition: http://www.idpf.org/vocab/rendition/#"> + <package version="3.0" xmlns="http://www.idpf.org/2007/opf" unique-identifier="bookid" xml:lang="%s"> <metadata - xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dc="http://purl.org/dc/elements/1.1/"> <dc:identifier id="bookid">urn:uuid:%s</dc:identifier> @@ -126,6 +164,7 @@ template outputEPub3() { <item id="css" href="%s" media-type="text/css"/> <item id="nav" href="toc_nav.xhtml" media-type="application/xhtml+xml" properties="nav" /> ┃", + doc.matters.src.language, _uuid, xhtml_format.special_characters_plain(doc.matters.conf_make_meta.meta.title_main), (doc.matters.conf_make_meta.meta.title_sub.empty) ? "" : format( @@ -145,14 +184,13 @@ template outputEPub3() { (pth_epub3.fn_oebps_css).chompPrefix("OEBPS/"), ); content ~= parts["manifest_documents"]; - // TODO sort jpg & png foreach (image; doc.matters.srcs.image_list) { - content ~= format(q"┃ <item id="%s" href="%s/%s" media-type="image/%s" /> + content ~= format(q"┃ <item id="%s" href="%s/%s" media-type="%s" /> ┃", - image.baseName.stripExtension, + _manifest_id("img", image.baseName.stripExtension), (pth_epub3.doc_oebps_image).chompPrefix("OEBPS/"), image, - image.extension.chompPrefix("."), + _image_media_type(image.extension.chompPrefix(".")), ); } content ~= " " ~ "</manifest>" ~ "\n "; @@ -251,8 +289,14 @@ template outputEPub3() { _new_title_set = true; } else { _new_title_set = false; + /+ ↓ a fragment only where there is one to reach. + A heading of level 4 or less is the top of its own + file, so the file is the target. A heading below + that sits inside a file and carries id="<ocn>", so + that is the fragment. An object with no ocn has no + id, and "#0" was pointing at nothing. +/ string _hashtag = ""; - if ((obj.metainfo.heading_lev_markup <= 4) && (obj.metainfo.ocn == 0)) { + if ((obj.metainfo.heading_lev_markup > 4) && (obj.metainfo.ocn > 0)) { _hashtag = "#" ~ obj.metainfo.ocn.to!string; } string _href = "<a href=\"" @@ -575,15 +619,15 @@ template outputEPub3() { ) { _segment_files_seen[obj.tags.segment_anchor_tag_epub] = true; oepbs_content_parts["manifest_documents"] ~= - format(q"┃<item id="%s.xhtml" href="%s.xhtml" media-type="application/xhtml+xml" /> + format(q"┃<item id="%s" href="%s.xhtml" media-type="application/xhtml+xml" /> ┃", - obj.tags.segment_anchor_tag_epub, + _manifest_id("seg", obj.tags.segment_anchor_tag_epub), obj.tags.segment_anchor_tag_epub, ); oepbs_content_parts["spine"] ~= - format(q"┃<itemref idref="%s.xhtml" linear="yes" /> + format(q"┃<itemref idref="%s" linear="yes" /> ┃", - obj.tags.segment_anchor_tag_epub, + _manifest_id("seg", obj.tags.segment_anchor_tag_epub), ); } } diff --git a/src/sisudoc/outputs/io_out/sqlite_collection_db.d b/src/sisudoc/outputs/io_out/sqlite_collection_db.d index d5b2dcf..f1556c4 100644 --- a/src/sisudoc/outputs/io_out/sqlite_collection_db.d +++ b/src/sisudoc/outputs/io_out/sqlite_collection_db.d @@ -789,35 +789,58 @@ template SQLiteFormatAndLoadObject() { string[] _table_cols; string _table; string _tablenote; + bool _in_head = false; + bool _in_body = false; foreach(row_idx, row; _table_rows) { _table_cols = row.split(rgx.table_delimiter_col); - _table ~= "<tr>"; - foreach(col_idx, cell; _table_cols) { - if ((_table_cols.length == 1) - && (_table_rows.length <= row_idx+2)) { // check row_idx+2 (rather than == ++row_idx) - _tablenote ~= cell; - } else { - string _col_is = (row_idx == 0 && obj.table.heading) ? "th" : "td"; - string _align = ("style=\"text-align:" - ~ ((obj.table.column_aligns[col_idx] == "l") - ? "left\"" : "right\"")); - _table ~= "<" - ~ _col_is - ~ " width=\"" - ~ obj.table.column_widths[col_idx].to!string - ~ "%\" " - ~ _align - ~ ">"; - _table ~= cell; - _table ~= "</" - ~ _col_is - ~ ">"; - } - } - _table ~= "</tr>"; + if ((_table_cols.length == 1) + && (_table_rows.length <= row_idx+2)) { // check row_idx+2 (rather than == ++row_idx) + _tablenote ~= _table_cols[0]; + continue; + } + /+ ↓ a heading row goes in <thead>, the rest in <tbody> +/ + if (row_idx == 0 && obj.table.heading) { + _table ~= "<thead>"; + _in_head = true; + } else if (!_in_body) { + if (_in_head) { _table ~= "</thead>"; _in_head = false; } + _table ~= "<tbody>"; + _in_body = true; + } + _table ~= "<tr>"; + foreach(col_idx, cell; _table_cols) { + bool _is_th = (row_idx == 0 && obj.table.heading); + string _col_is = _is_th ? "th" : "td"; + string _class = (col_idx < obj.table.column_aligns.length + && obj.table.column_aligns[col_idx] == "l") ? "left" : "right"; + _table ~= "<" + ~ _col_is + ~ (_is_th ? " scope=\"col\"" : "") + ~ " class=\"" + ~ _class + ~ "\">"; + _table ~= cell; + _table ~= "</" + ~ _col_is + ~ ">"; } + _table ~= "</tr>"; + } + if (_in_head) { _table ~= "</thead>"; } + else if (_in_body) { _table ~= "</tbody>"; } + /+ ↓ column widths as a <colgroup>, not a width attribute on every cell +/ + string _colgroup; + if (obj.table.column_widths.length > 0) { + string _cols; + foreach(w; obj.table.column_widths) { + _cols ~= (w > 0) + ? "<col style=\"width:" ~ w.to!string ~ "%\" />" + : "<col />"; + } + _colgroup = "<colgroup>" ~ _cols ~ "</colgroup>"; + } Tuple!(string, string) t = tuple( - _table, + (_colgroup ~ _table), _tablenote, ); return t; @@ -826,15 +849,15 @@ template SQLiteFormatAndLoadObject() { Tuple!(string, string) t = _tablarize(obj, _txt); _txt = t[0]; string _note = t[1]; - string o = format(q"┃<p class="%s"> - <table summary="normal text css" width="95%%" border="0" cellpadding="2" align="center"> + string o = format(q"┃<div class="%s"> + <table class="table"> %s </table> %s - </p>┃", + </div>┃", obj.metainfo.is_a, _txt, - _note + (_note.strip.empty) ? "" : ("<p class=\"tablenote\">" ~ _note.strip ~ "</p>") ); return o; } diff --git a/src/sisudoc/outputs/io_out/xmls.d b/src/sisudoc/outputs/io_out/xmls.d index 097ce44..c1e733e 100644 --- a/src/sisudoc/outputs/io_out/xmls.d +++ b/src/sisudoc/outputs/io_out/xmls.d @@ -205,6 +205,17 @@ template outputXHTMLs() { .replaceAll(rgx.inline_cite, ("<cite>$1</cite>")); return _txt; } + /+ ↓ the heading element for a markup level. + Markup goes to level 7; HTML stops at h6, and an <h7> is simply + not an element, so the deepest three markup levels share h6 and + are told apart by the "heading" class and their ocn. Level 0 is + the document title, which is h1 in a segment of its own. + +/ + int _heading_element_level(O)(O obj, string _xml_type) { + int _lev = obj.metainfo.heading_lev_markup.to!int; + if (_xml_type == "epub" && _lev == 0) { return 1; } + return (_lev > 6) ? 6 : _lev; + } string _xhtml_anchor_tags(O)(O obj) { string tags=""; if (obj.tags.anchor_tags.length > 0) { @@ -495,13 +506,13 @@ string tail(M)(M doc_matters) { string o; o = format(q"┃<hr /> <div class="rights"> - <p class="small" id="copyright"> + <p class="small" id="doc_footer_copyright"> <b>Copyright:</b> %s </p> </div> %s <div class="rights"> - <p class="small" id="rights"> + <p class="small" id="doc_footer_rights"> %s </p> </div> @@ -579,7 +590,9 @@ string tail(M)(M doc_matters) { if (_xml_type == "seg" || _xml_type == "epub") { seg_lvs = (_xml_type == "epub") ? "seg_lv1to4" : "seg_lv4"; foreach (m; _txt.match(rgx.inline_link_hash)) { - if (m.captures["hash"] in doc_matters.has.tag_associations) { + if ((m.captures["hash"] in doc_matters.has.tag_associations) + && (seg_lvs in doc_matters.has.tag_associations[(m.captures["hash"])]) + ) { if ( m.captures["hash"] == doc_matters.has.tag_associations[(m.captures["hash"])][seg_lvs] @@ -928,15 +941,13 @@ string tail(M)(M doc_matters) { (doc_matters.opt.action.ocn_off) ? "" : ((obj.metainfo.object_number.empty) ? "" : obj.metainfo.identifier), - ((_xml_type == "epub" && obj.metainfo.heading_lev_markup == 0) ? 1 - : obj.metainfo.heading_lev_markup), + _heading_element_level(obj, _xml_type), obj.metainfo.is_a, obj.metainfo.identifier, tags, heading_lev_anchor_tag, _txt, - ((_xml_type == "epub" && obj.metainfo.heading_lev_markup == 0) ? 1 - : obj.metainfo.heading_lev_markup), + _heading_element_level(obj, _xml_type), ); } else { o ~= format(q"┃%s @@ -946,14 +957,12 @@ string tail(M)(M doc_matters) { </h%s> </div>┃", _horizontal_rule, - ((_xml_type == "epub" && obj.metainfo.heading_lev_markup == 0) ? 1 - : obj.metainfo.heading_lev_markup), + _heading_element_level(obj, _xml_type), obj.metainfo.is_a, tags, heading_lev_anchor_tag, _txt, - ((_xml_type == "epub" && obj.metainfo.heading_lev_markup == 0) ? 1 - : obj.metainfo.heading_lev_markup), + _heading_element_level(obj, _xml_type), ); } return o; @@ -1316,6 +1325,17 @@ string tail(M)(M doc_matters) { ); return u; } + /+ ↓ column widths as a <colgroup>, not a width attribute on every cell +/ + string _table_colgroup(O)(const O obj) { + if (obj.table.column_widths.length == 0) { return ""; } + string _cols; + foreach(w; obj.table.column_widths) { + _cols ~= (w > 0) + ? "<col style=\"width:" ~ w.to!string ~ "%\" />" + : "<col />"; + } + return "<colgroup>" ~ _cols ~ "</colgroup>"; + } Tuple!(string, string) tablarize(O)( string _txt, const O obj, @@ -1324,27 +1344,42 @@ string tail(M)(M doc_matters) { string[] _table_cols; string _table; string _tablenote; + bool _in_head = false; + bool _in_body = false; foreach(row_idx, row; _table_rows) { _table_cols = row.split(rgx.table_delimiter_col); + if ((_table_cols.length == 1) + && (_table_rows.length <= row_idx+2)) { + _tablenote ~= _table_cols[0]; + continue; + } + /+ ↓ a heading row goes in <thead>, the rest in <tbody> +/ + if (row_idx == 0 && obj.table.heading) { + _table ~= "<thead>"; + _in_head = true; + } else if (!_in_body) { + if (_in_head) { _table ~= "</thead>"; _in_head = false; } + _table ~= "<tbody>"; + _in_body = true; + } _table ~= "<tr>"; foreach(col_idx, cell; _table_cols) { - if ((_table_cols.length == 1) - && (_table_rows.length <= row_idx+2)) { - _tablenote ~= cell; - } else { - string _col_is = (row_idx == 0 && obj.table.heading) ? "th" : "td"; - string _align = ("style=\"text-align:" - ~ ((obj.table.column_aligns[col_idx] == "l") - ? "left\"" : "right\"")); - _table ~= "<" ~ _col_is ~ " width=\"" ~ obj.table.column_widths[col_idx].to!string ~ "%\" " ~ _align ~ ">"; - _table ~= cell; - _table ~= "</" ~ _col_is ~ ">"; - } + bool _is_th = (row_idx == 0 && obj.table.heading); + string _col_is = _is_th ? "th" : "td"; + string _class = (col_idx < obj.table.column_aligns.length + && obj.table.column_aligns[col_idx] == "l") ? "left" : "right"; + _table ~= "<" ~ _col_is + ~ (_is_th ? " scope=\"col\"" : "") + ~ " class=\"" ~ _class ~ "\">"; + _table ~= cell; + _table ~= "</" ~ _col_is ~ ">"; } _table ~= "</tr>"; } + if (_in_head) { _table ~= "</thead>"; } + else if (_in_body) { _table ~= "</tbody>"; } Tuple!(string, string) t = tuple( - _table, + (_table_colgroup(obj) ~ _table), _tablenote, ); return t; @@ -1366,12 +1401,12 @@ string tail(M)(M doc_matters) { string o; o = format(q"┃ <div class="substance"> <label class="ocn"><a href="#%s" class="lnkocn">%s</a></label> - <p class="%s" id="%s">%s - <table summary="normal text css" width="95%%" border="0" cellpadding="2" align="center"> + <div class="%s" id="%s">%s + <table class="table"> %s </table> %s - </p> + </div> </div>┃", obj.metainfo.object_number, (doc_matters.opt.action.ocn_off) ? "" : ((obj.metainfo.object_number.empty) ? "" : obj.metainfo.identifier), @@ -1379,7 +1414,7 @@ string tail(M)(M doc_matters) { obj.metainfo.object_number, tags, _txt, - _note + (_note.strip.empty) ? "" : ("<p class=\"tablenote\">" ~ _note.strip ~ "</p>") ); return o; } diff --git a/src/sisudoc/outputs/io_out/xmls_css.d b/src/sisudoc/outputs/io_out/xmls_css.d index ed9f994..6cab68e 100644 --- a/src/sisudoc/outputs/io_out/xmls_css.d +++ b/src/sisudoc/outputs/io_out/xmls_css.d @@ -880,6 +880,24 @@ table { margin-right : 2em; background-color : inherit; } +div.table { + margin : 1em 0; + overflow-x : auto; +} +table.table { + display : table; + width : 95%%; + margin : 0 auto; + border-collapse : collapse; + background-color : inherit; +} +table.table th, table.table td { + padding : 2px; + vertical-align : top; +} +p.tablenote { + margin : 0.5em 0 0 0; +} tr { } th,td { vertical-align : top; @@ -1668,6 +1686,24 @@ table { margin-right : 2em; background-color : inherit; } +div.table { + margin : 1em 0; + overflow-x : auto; +} +table.table { + display : table; + width : 95%%; + margin : 0 auto; + border-collapse : collapse; + background-color : inherit; +} +table.table th, table.table td { + padding : 2px; + vertical-align : top; +} +p.tablenote { + margin : 0.5em 0 0 0; +} tr { } th,td { vertical-align : top; @@ -2467,6 +2503,24 @@ table { margin-right : 2em; background-color : inherit; } +div.table { + margin : 1em 0; + overflow-x : auto; +} +table.table { + display : table; + width : 95%%; + margin : 0 auto; + border-collapse : collapse; + background-color : inherit; +} +table.table th, table.table td { + padding : 2px; + vertical-align : top; +} +p.tablenote { + margin : 0.5em 0 0 0; +} tr { } th,td { vertical-align : top; @@ -3181,6 +3235,24 @@ table { margin-right : 2em; background-color : inherit; } +div.table { + margin : 1em 0; + overflow-x : auto; +} +table.table { + display : table; + width : 95%%; + margin : 0 auto; + border-collapse : collapse; + background-color : inherit; +} +table.table th, table.table td { + padding : 2px; + vertical-align : top; +} +p.tablenote { + margin : 0.5em 0 0 0; +} tr { } th,td { vertical-align : top; @@ -3906,6 +3978,24 @@ table { margin-right : 2em; background-color : inherit; } +div.table { + margin : 1em 0; + overflow-x : auto; +} +table.table { + display : table; + width : 95%%; + margin : 0 auto; + border-collapse : collapse; + background-color : inherit; +} +table.table th, table.table td { + padding : 2px; + vertical-align : top; +} +p.tablenote { + margin : 0.5em 0 0 0; +} tr { } th,td { vertical-align : top; @@ -4460,6 +4550,24 @@ table { margin-right : 2em; background-color : inherit; } +div.table { + margin : 1em 0; + overflow-x : auto; +} +table.table { + display : table; + width : 95%%; + margin : 0 auto; + border-collapse : collapse; + background-color : inherit; +} +table.table th, table.table td { + padding : 2px; + vertical-align : top; +} +p.tablenote { + margin : 0.5em 0 0 0; +} tr { } th,td { vertical-align : top; diff --git a/test/reference/abstraction/content.cory_doctorow.en.ssp b/test/reference/abstraction/content.cory_doctorow.en.ssp index 38a8fe1..a829af2 100644 --- a/test/reference/abstraction/content.cory_doctorow.en.ssp +++ b/test/reference/abstraction/content.cory_doctorow.en.ssp @@ -2536,7 +2536,7 @@ .is_of_type: para .sha256: E0F04412996A5887BE496D9455ADFB93769A4861D8F64A9BC867A3C57971DE88 .segment: seg_2 -.heading_lev_anchor: x- +.heading_lev_anchor: x--73 .segment_epub: seg_2 .segment_html_is: seg_2 .segment_epub_is: seg_2 @@ -2882,7 +2882,7 @@ .is_of_type: para .sha256: 12D04772E32C49C982DCFC34458FE7D1DB754A6BEFC7E321DFE8FBF7B747DC47 .segment: seg_2 -.heading_lev_anchor: x- +.heading_lev_anchor: x--100 .segment_epub: seg_2 .segment_html_is: seg_2 .segment_epub_is: seg_2 @@ -3000,7 +3000,7 @@ .is_of_type: para .sha256: C346CFE219158190D638C00CC0F7DAAC959E755F9D8CDC5EBB746806C943AB5B .segment: seg_2 -.heading_lev_anchor: x- +.heading_lev_anchor: x--108 .segment_epub: seg_2 .segment_html_is: seg_2 .segment_epub_is: seg_2 @@ -3476,7 +3476,7 @@ .is_of_type: para .sha256: AE2405DF403554C65B7631871B0F2EDD8C8E49F8318965F179ED900EB2D33A67 .segment: seg_2 -.heading_lev_anchor: x- +.heading_lev_anchor: x--145 .segment_epub: seg_2 .segment_html_is: seg_2 .segment_epub_is: seg_2 @@ -7531,7 +7531,7 @@ .is_of_type: para .sha256: 6E62EE82E3DF2A7DFCABA91E18EAB2A77C9C7F7B4A5DCEB49528346078B636D2 .segment: seg_15 -.heading_lev_anchor: x- +.heading_lev_anchor: x--440 .segment_epub: seg_15 .segment_html_is: seg_15 .segment_epub_is: seg_15 @@ -7588,7 +7588,7 @@ .is_of_type: para .sha256: 435168BDFA62B2A21AE519C224BAE9E63FAA5C3131E18403BAC6383B61A438C0 .segment: seg_15 -.heading_lev_anchor: x- +.heading_lev_anchor: x--444 .segment_epub: seg_15 .segment_html_is: seg_15 .segment_epub_is: seg_15 @@ -7620,7 +7620,7 @@ .is_of_type: para .sha256: 2B0C1510AFFB174A55A502270FCD30FC8A245B9ADEF468A2A445DF444CF5841A .segment: seg_15 -.heading_lev_anchor: x- +.heading_lev_anchor: x--446 .segment_epub: seg_15 .segment_html_is: seg_15 .segment_epub_is: seg_15 @@ -7728,7 +7728,7 @@ .is_of_type: para .sha256: 8A281794EBDA231325CB10A6F1908E1AE6DDA6560A379B7EE8C02C28CBCEBBC9 .segment: seg_15 -.heading_lev_anchor: x- +.heading_lev_anchor: x--454 .segment_epub: seg_15 .segment_html_is: seg_15 .segment_epub_is: seg_15 @@ -7796,7 +7796,7 @@ .is_of_type: para .sha256: B2C6211B1EAB3298CBBF4A47C6E4F40B897D6F1E53E98D6A2F260CFFDEC7D4DD .segment: seg_15 -.heading_lev_anchor: x- +.heading_lev_anchor: x--459 .segment_epub: seg_15 .segment_html_is: seg_15 .segment_epub_is: seg_15 @@ -7852,7 +7852,7 @@ .is_of_type: para .sha256: DB233F1FB52CB27629E4A008D361A0F9B138287A6E6B2549F625CC3C3F26F04E .segment: seg_15 -.heading_lev_anchor: x- +.heading_lev_anchor: x--463 .segment_epub: seg_15 .segment_html_is: seg_15 .segment_epub_is: seg_15 @@ -7932,7 +7932,7 @@ .is_of_type: para .sha256: 2E2FF925CC1322BFFFA8826779F2C23D6C32C67AE4E99E6B01508BF9AD9B6BA4 .segment: seg_15 -.heading_lev_anchor: x- +.heading_lev_anchor: x--469 .segment_epub: seg_15 .segment_html_is: seg_15 .segment_epub_is: seg_15 @@ -8100,7 +8100,7 @@ .is_of_type: para .sha256: 7C9EF24634EC4796B19AE4B1F81D4D404A896CDB1202AFC0098BA0C54CAA61BE .segment: seg_15 -.heading_lev_anchor: x- +.heading_lev_anchor: x--479 .segment_epub: seg_15 .segment_html_is: seg_15 .segment_epub_is: seg_15 @@ -8156,7 +8156,7 @@ .is_of_type: para .sha256: 8BC8808A857028DB86C62FF2A59EF1D667EFBFB0AAECB3E9E548962DD47D450F .segment: seg_15 -.heading_lev_anchor: x- +.heading_lev_anchor: x--483 .segment_epub: seg_15 .segment_html_is: seg_15 .segment_epub_is: seg_15 @@ -8236,7 +8236,7 @@ .is_of_type: para .sha256: 48CED3C978FDDAE04931DDFD52440553664432F7ECCD63F36F52B851C173C6C3 .segment: seg_15 -.heading_lev_anchor: x- +.heading_lev_anchor: x--489 .segment_epub: seg_15 .segment_html_is: seg_15 .segment_epub_is: seg_15 diff --git a/test/reference/abstraction/live-manual.es.ssp b/test/reference/abstraction/live-manual.es.ssp index 2fb8833..a3b3c06 100644 --- a/test/reference/abstraction/live-manual.es.ssp +++ b/test/reference/abstraction/live-manual.es.ssp @@ -4278,7 +4278,7 @@ .is_of_type: para .sha256: 2B5F530EEC4D1A1505FC965B9D2E24E9E3C23ECB5BD5DEEC94DDCD5F667F555C .segment: the-basics -.heading_lev_anchor: using-iso-hybrid +.heading_lev_anchor: using-iso-hybrid-189 .segment_epub: the-basics .segment_html_is: the-basics .segment_epub_is: the-basics diff --git a/test/reference/abstraction/the_public_domain.james_boyle.en.ssp b/test/reference/abstraction/the_public_domain.james_boyle.en.ssp index 675fb34..b7a67d2 100644 --- a/test/reference/abstraction/the_public_domain.james_boyle.en.ssp +++ b/test/reference/abstraction/the_public_domain.james_boyle.en.ssp @@ -1612,7 +1612,7 @@ .is_of_type: para .sha256: E963CE2FEE8900892828081A301481CCEF0B6D0BCD4F95A3EFC5673A4512AD00 .segment: chapter_1 -.heading_lev_anchor: chapter_1 +.heading_lev_anchor: chapter_1-81 .segment_epub: chapter_1 .segment_html_is: chapter_1 .segment_epub_is: chapter_1 @@ -2957,7 +2957,7 @@ .is_of_type: para .sha256: 9D02B0A0B1E2650828466A4FCD99FFE09873F72238DB5C4D3C7F226879FF83F9 .segment: chapter_2 -.heading_lev_anchor: chapter_2 +.heading_lev_anchor: chapter_2-184 .segment_epub: chapter_2 .segment_html_is: chapter_2 .segment_epub_is: chapter_2 @@ -3586,7 +3586,7 @@ .is_of_type: para .sha256: BE74615A73024FD20DBAAFD69D37E816AA338403293F0B85E3BDD73294B3B565 .segment: chapter_3 -.heading_lev_anchor: chapter_3 +.heading_lev_anchor: chapter_3-230 .segment_epub: chapter_3 .segment_html_is: chapter_3 .segment_epub_is: chapter_3 @@ -5043,7 +5043,7 @@ .is_of_type: para .sha256: 1AE5FFF4E1337498417EA656E69BE2134C39F6452004E8C41487D3301D0E61FF .segment: chapter_4 -.heading_lev_anchor: chapter_4 +.heading_lev_anchor: chapter_4-344 .segment_epub: chapter_4 .segment_html_is: chapter_4 .segment_epub_is: chapter_4 @@ -6750,7 +6750,7 @@ .is_of_type: para .sha256: 9DA46DA5A083E19F6842572DB65B18C985DDD9491BEE6358D8871EE22FA3F82A .segment: chapter_5 -.heading_lev_anchor: chapter_5 +.heading_lev_anchor: chapter_5-479 .segment_epub: chapter_5 .segment_html_is: chapter_5 .segment_epub_is: chapter_5 @@ -8591,7 +8591,7 @@ .is_of_type: para .sha256: E3653EBCD3DC67EF44731D2E2537AAE91545AC625FD36797828BD687F2AFA4B6 .segment: chapter_6 -.heading_lev_anchor: chapter_6 +.heading_lev_anchor: chapter_6-617 .segment_epub: chapter_6 .segment_html_is: chapter_6 .segment_epub_is: chapter_6 @@ -9671,7 +9671,7 @@ .is_of_type: para .sha256: 69A12F94F0BA03913A00400418D427CA970696E3DF3C8C2F4D48F1C74C783FAF .segment: chapter_7 -.heading_lev_anchor: chapter_7 +.heading_lev_anchor: chapter_7-699 .segment_epub: chapter_7 .segment_html_is: chapter_7 .segment_epub_is: chapter_7 @@ -10769,7 +10769,7 @@ .is_of_type: para .sha256: CB18592BF9C536CEECB58E13B2E2F18D85ED509FF62474A4B783E04C3AF07BC9 .segment: chapter_8 -.heading_lev_anchor: chapter_8 +.heading_lev_anchor: chapter_8-785 .segment_epub: chapter_8 .segment_html_is: chapter_8 .segment_epub_is: chapter_8 @@ -12083,7 +12083,7 @@ .is_of_type: para .sha256: CBC4E874A0AAC1856EAEC8E0979DABD8A211F4AC76D5ABF10A04A8C54A012D74 .segment: chapter_9 -.heading_lev_anchor: chapter_9 +.heading_lev_anchor: chapter_9-887 .segment_epub: chapter_9 .segment_html_is: chapter_9 .segment_epub_is: chapter_9 @@ -13106,7 +13106,7 @@ .is_of_type: para .sha256: 1142480E6C32D2754F1A1718AE249C69D6949428FAAF23E18F27DD3F3A82033A .segment: chapter_10 -.heading_lev_anchor: chapter_10 +.heading_lev_anchor: chapter_10-964 .segment_epub: chapter_10 .segment_html_is: chapter_10 .segment_epub_is: chapter_10 diff --git a/test/test-epub-validity.sh b/test/test-epub-validity.sh index 4bc5729..b3fde21 100755 --- a/test/test-epub-validity.sh +++ b/test/test-epub-validity.sh @@ -34,13 +34,17 @@ SPINE_DIR="$(cd "$SCRIPT_DIR/.." && pwd)" # markup and left an unbalanced </a> behind - was a url boundary defect in # the abstraction, and is fixed. # -# The errors that remain are, in order of how many: -# the table writer's obsolete presentational attributes, width on every -# cell and summary/border/cellpadding/align on the table; the navigation -# document linking to "#0", a fragment that is never defined; duplicate -# ids; a table inside a <p>; an opf id containing a colon. +# No error is allowed either, and none is outstanding. Both numbers being +# zero is the point: anything at all that epubcheck calls an error is a +# regression, and there is no list to add to. +# +# Two warnings remain and are not counted here. Both are NAV-011 in the +# same shape, in two documents: the navigation document lists one file +# twice, and the repeat is behind the previous entry in spine order. It +# comes from how the endnotes part and section headings are ordered, not +# from the navigation writer. FATALS_ALLOWED=${SpineEpubFatalsAllowed:-0} -ERRORS_ALLOWED=${SpineEpubErrorsAllowed:-1312} +ERRORS_ALLOWED=${SpineEpubErrorsAllowed:-0} if [ -z "$SpinePOD" ]; then echo "ERROR: \$SpinePOD is not set." >&2 |
