aboutsummaryrefslogtreecommitdiffhomepage
path: root/src/sisudoc/outputs
diff options
context:
space:
mode:
Diffstat (limited to 'src/sisudoc/outputs')
-rw-r--r--src/sisudoc/outputs/io_out/epub3.d68
-rw-r--r--src/sisudoc/outputs/io_out/sqlite_collection_db.d81
-rw-r--r--src/sisudoc/outputs/io_out/xmls.d91
-rw-r--r--src/sisudoc/outputs/io_out/xmls_css.d108
4 files changed, 279 insertions, 69 deletions
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;
generated by cgit v1.2.3 (git 2.25.1) at 2026-10-08 08:56:49 +0000