diff options
author | Ralph Amissah <ralph.amissah@gmail.com> | 2021-06-27 16:59:44 -0400 |
---|---|---|
committer | Ralph Amissah <ralph.amissah@gmail.com> | 2021-08-01 07:46:58 -0400 |
commit | 4d5ee2ead874c7a436faa8754eb99215927ea94d (patch) | |
tree | c1519c0b8db2302bcf46ffdce04a6580d7a012e5 /misc/util/d/tools/markup_conversion/markup_changes_header_and_content.d | |
parent | org-mode code block headers (diff) |
dir rename ./sundry (from ./misc)
Diffstat (limited to 'misc/util/d/tools/markup_conversion/markup_changes_header_and_content.d')
-rwxr-xr-x | misc/util/d/tools/markup_conversion/markup_changes_header_and_content.d | 244 |
1 files changed, 0 insertions, 244 deletions
diff --git a/misc/util/d/tools/markup_conversion/markup_changes_header_and_content.d b/misc/util/d/tools/markup_conversion/markup_changes_header_and_content.d deleted file mode 100755 index 86792ff..0000000 --- a/misc/util/d/tools/markup_conversion/markup_changes_header_and_content.d +++ /dev/null @@ -1,244 +0,0 @@ -#!/usr/bin/env rdmd -/+ - - read in file .sst .ssi .ssm - - loop twice - - first - - check for and skip code blocks - - use unique code marker for endnote markers in text and give an endnote - number ★1, increment - - extract all endnotes in array - - second - - check that the footnote marker number count matches the number of notes - in the array - - if they match either: - - substitute each endnote marker with the array footnote[number-1] - - substitute each endnote marker with footnote - as inlined footnote markup (footnote number not needed) - - if they do not match exit - - check whether changes have been made - - if so write file with inline footnotes in sub-directory converted_output_/ - using the same name as the original file - - else, exit -+/ -import std.stdio; -import std.file; -import std.array : split; -import std.exception; -// import std.range; -import core.stdc.errno; -import std.regex; -import std.format; -import std.conv; -void main(string[] args) { - static heading_a = ctRegex!(`^:?[A][~] `, "m"); - static comment = ctRegex!(`^%+ `); - static block_tic_code_open = ctRegex!("^`{3} code(?:[.](?P<syntax>[a-z][0-9a-z#+_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?"); - static block_tic_close = ctRegex!("^(`{3})$","m"); - static block_curly_code_open = ctRegex!(`^(?:code(?:[.](?P<syntax>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$)`); - static block_curly_code_close = ctRegex!(`^([}]code)`); - auto rgx_endnote_ref = ctRegex!(`([~]\^)(?P<tail>[)\]]? |$)`, "gm"); - auto rgx_endnote = ctRegex!(`^\^~\s+(.+|\n)`, "gm"); - char[][] header0Content1(in string src_text) { // cast(char[]) - /+ split string on _first_ match of "^:?A~\s" into [header, content] array/tuple +/ - char[][] header_and_content; - auto m = (cast(char[]) src_text).matchFirst(heading_a); - header_and_content ~= m.pre; - header_and_content ~= m.hit ~ m.post; - assert(header_and_content.length == 2, - "document markup is broken, header body split == " - ~ header_and_content.length.to!string - ~ "; (header / body array split should == 2 (split is on level A~))" - ); - return header_and_content; - } - foreach(arg; args[1..$]) { - if ( - !(arg.match(regex(r"--\w+"))) - && arg.match(regex(r"\w+?\.ss[itm]")) - ) { - writeln(arg); - string filename = arg; - try { - string[] munged_header, munged_contents, munged_endnotes, endnote_refs; - string text = filename.readText; - char[][] hc = header0Content1(text); - char[] src_header = hc[0]; - string[] headers = src_header.to!string.split("\n\n"); - char[] src_txt = hc[1]; - string[] paragraphs = src_txt.to!string.split("\n\n"); - int endnote_ref_count = 0; - int[string] type = [ - "curly_code" : 0, - "tic_code" : 0, - ]; - string _tmp_header; - foreach (h_; headers) { /+ loop to inline endnotes +/ - _tmp_header = ""; - if (h_.match(regex(r"^[@\[]?title[:\]]?"))) { // title - if (auto m = h_.match(regex(r"^@title:(?:\s+(?P<c>.+)|$)"))) { // sisu bespoke markup - if (m.captures["c"].length == 0) { - _tmp_header ~= "title:"; - } else { - _tmp_header ~= "title:\n main: " ~ "\"" ~ m.captures["c"] ~ "\""; - } - } else if (auto m = h_.match(regex(r"^title\s*=\s*(?P<c>.+)"))) { // toml? - if (m.captures["c"].length == 0) { - _tmp_header ~= "title:"; - } else { - _tmp_header ~= "title:\n main: " ~ "\"" ~ m.captures["c"] ~ "\""; - } - } else if (auto m = h_.match(regex(r"^\[title\]"))) { // toml markup - _tmp_header ~= "title:"; - } else if (auto m = h_.match(regex(r"^title(?:\s+(?P<c>.+)|\s+\\$)"))) { // sdlang markup - if (m.captures["c"].length == 0) { - _tmp_header ~= "title:"; - } else { - _tmp_header ~= "title:\n main: " ~ "\"" ~ m.captures["c"] ~ "\""; - } - } - if (h_.match(regex(r"^\s*[:]?(?:main)[:= ]?", "m"))) { - if (auto m = h_.match(regex(r"^\s+(?P<h>:main):(?:\s+(?P<c>.+)|$)", "m"))) { // sisu bespoke markup - _tmp_header ~= " main: " ~ "\"" ~ m.captures["c"] ~ "\""; - } else if (auto m = h_.match(regex(r"^\s*(?P<h>main)\s*=\s*(?P<c>.+)", "m"))) { // toml? - _tmp_header ~= " main: " ~ m.captures["c"]; - } else if (auto m = h_.match(regex(r"^\s+(?P<h>main)(?:\s*\s*(?P<c>.+)|$)", "m"))) { // toml markup - _tmp_header ~= " main: " ~ "\"" ~ m.captures["c"] ~ "\""; - } else if (auto m = h_.match(regex(r"^\s+(?P<h>main)(?:\s+(?P<c>.+)|\s+\\$)", "m"))) { // sdlang markup - _tmp_header ~= " main: " ~ "\"" ~ m.captures["c"] ~ "\""; - } - } - if (h_.match(regex(r"^\s*[:]?(?:sub(title)?)[:= ]?", "m"))) { - if (auto m = h_.match(regex(r"^\s+:sub(?:title)?:(?:\s+(?P<c>.+)|$)", "m"))) { // sisu bespoke markup - _tmp_header ~= " subtitle: " ~ "\"" ~ m.captures["c"] ~ "\""; - } else if (auto m = h_.match(regex(r"^\s*sub(?:title)?\s*=\s*(?P<c>.+)$", "m"))) { // toml? - _tmp_header ~= " subtitle: " ~ m.captures["c"]; - } else if (auto m = h_.match(regex(r"^\s+(?:title)?(?:\s*\s*(?P<c>.+)|$)", "m"))) { // toml markup - _tmp_header ~= " subtitle: " ~ "\"" ~ m.captures["c"] ~ "\""; - } else if (auto m = h_.match(regex(r"^\s+(?:title)?(?:\s+(?P<c>.+)|\s+\\$)", "m"))) { // sdlang markup - _tmp_header ~= " subtitle: " ~ "\"" ~ m.captures["c"] ~ "\""; - } - } - } - if (h_.match(regex(r"^[@\[]?rights[:\]]?"))) { // rights - if (auto m = h_.match(regex(r"^@rights:[ ]+(?P<c>.+)$"))) { // sisu bespoke markup - _tmp_header ~= "rights: \n copyright: \"" ~ m.captures["c"] ~ "\""; - } else if (auto m = h_.match(regex(r"^@rights:"))) { // sisu bespoke markup - _tmp_header ~= "rights:"; - } else if (auto m = h_.match(regex(r"^\[rights\]", "m"))) { // toml markup - _tmp_header ~= "rights:"; - } else if (auto m = h_.match(regex(r"^rights:"))) { // sdlang markup - _tmp_header ~= "rights:"; - } - if (h_.match(regex(r"^\s*[:]?copyright[:= ]?", "m"))) { - if (auto m = h_.match(regex(r"^\s+:copyright:(?:\s+(?P<c>.+)|$)", "m"))) { // sisu bespoke markup - _tmp_header ~= " copyright: " ~ "\"" ~ m.captures["c"] ~ "\""; - } else if (auto m = h_.match(regex(r"^\s*copyright\s*=\s*(?P<c>.+)", "m"))) { // toml? - _tmp_header ~= " copyright: " ~ m.captures["c"]; - } else if (auto m = h_.match(regex(r"^\s+<h>copyright(?:\s*\s*(?P<c>.+)|$)", "m"))) { // toml markup - _tmp_header ~= " copyright: " ~ "\"" ~ m.captures["c"] ~ "\""; - } else if (auto m = h_.match(regex(r"^\s+copyright(?:\s+(?P<c>.+)|\s+\\$)", "m"))) { // sdlang markup - _tmp_header ~= " copyright: " ~ "\"" ~ m.captures["c"] ~ "\""; - } - } - if (h_.match(regex(r"^\s*[:]?licen[cs]e[:= ]?", "m"))) { - if (auto m = h_.match(regex(r"^\s+:licen[cs]e:(?:\s+(?P<c>.+)|$)", "m"))) { // sisu bespoke markup - _tmp_header ~= " license: " ~ "\"" ~ m.captures["c"] ~ "\""; - } else if (auto m = h_.match(regex(r"^\s*licen[cs]e\s*=\s*(?P<c>.+)$", "m"))) { // toml? - _tmp_header ~= " license: " ~ m.captures["c"]; - } else if (auto m = h_.match(regex(r"^\s+licen[cs]e(?:\s*\s*(?P<c>.+)|$)", "m"))) { // toml markup - _tmp_header ~= " license: " ~ "\"" ~ m.captures["c"] ~ "\""; - } else if (auto m = h_.match(regex(r"^\s+licen[cs]e(?:\s+(?P<c>.+)|\s+\\$)", "m"))) { // sdlang markup - _tmp_header ~= " license: " ~ "\"" ~ m.captures["c"] ~ "\""; - } - } - } - if (_tmp_header.length > 0) { - munged_header ~= _tmp_header; - } else { - munged_header ~= h_; - } - } - writeln(munged_header); - foreach (paragraph; paragraphs) { /+ loop to gather binary endnotes +/ - if ( !( type["curly_code"] == 1 || type["tic_code"] == 1) - && paragraph.match(rgx_endnote) - ) { - munged_endnotes ~= replaceAll!(m => m[1]) - (paragraph, rgx_endnote); - } else { - if ( type["curly_code"] == 1 || type["tic_code"] == 1 - || paragraph.matchFirst(block_curly_code_open) - || paragraph.matchFirst(block_tic_code_open) - ) { /+ code blocks identified, no munging +/ - if ( type["curly_code"] == 1 - && paragraph.matchFirst(block_curly_code_close) - ) { - type["curly_code"] = 0; - } else if (type["tic_code"] == 1 - && paragraph.matchFirst(block_tic_close) - ) { - type["tic_code"] = 0; - } else if (paragraph.matchFirst(block_curly_code_open)) { - type["curly_code"] = 1; - } else if (paragraph.matchFirst(block_tic_code_open)) { - type["tic_code"] = 1; - } - munged_contents ~= paragraph; - } else { /+ regular content, not a code block +/ - if (auto m = paragraph.matchAll(rgx_endnote_ref)) { - foreach (n; m) { - endnote_ref_count++; // endnote_refs ~= (n.captures[1]); - } - } - paragraph = replaceAll!(m => " \\\\ " ) - (paragraph, regex(r"\s*<(?:/\s*|:)?br>\s*")); // (paragraph, regex(r"(<br>)")); - munged_contents ~= paragraph; - } - } - } - { - import std.outbuffer; - auto buffer = new OutBuffer(); - foreach (header; munged_header) { /+ loop to inline endnotes +/ - buffer.write(header ~ "\n\n"); - } - if (munged_endnotes.length == endnote_ref_count) { - int endnote_count = -1; - foreach (content; munged_contents) { /+ loop to inline endnotes +/ - content = replaceAll!(m => "~{ " ~ munged_endnotes[++endnote_count] ~ " }~" ~ m["tail"] ) - (content, rgx_endnote_ref); // endnote_ref cannot occur in a code block or else fail - buffer.write(content ~ "\n\n"); - } - if (buffer) { - try { - string dir_out = "converted_output_"; - string path_and_file_out = dir_out ~ "/" ~ filename; - dir_out.mkdirRecurse; - auto f = File(path_and_file_out, "w"); - f.write(buffer); - // writeln("wrote: ", path_and_file_out); - } catch (FileException ex) { - writeln("did not write file"); - // Handle errors - } - } - } else { - foreach (content; munged_contents) { /+ loop to inline endnotes +/ - buffer.write(content ~ "\n\n"); - } - } - } - } catch (ErrnoException ex) { - switch(ex.errno) { - case EPERM: - case EACCES: // Permission denied - break; - case ENOENT: // File does not exist - break; - default: // Handle other errors - break; - } - } - } - } -} |