aboutsummaryrefslogtreecommitdiffhomepage
path: root/org/default_regex.org
diff options
context:
space:
mode:
authorRalph Amissah <ralph.amissah@gmail.com>2020-01-24 15:42:37 -0500
committerRalph Amissah <ralph.amissah@gmail.com>2020-02-11 13:08:49 -0500
commit52049eb825cca32a2d2e6596fe5160b3f33ba74d (patch)
treea6ab8c57bf455f30f7de20dbf87c15bf55274bdf /org/default_regex.org
parentdlang safe default imminent, look ahead (diff)
update headers and year
Diffstat (limited to 'org/default_regex.org')
-rw-r--r--org/default_regex.org90
1 files changed, 45 insertions, 45 deletions
diff --git a/org/default_regex.org b/org/default_regex.org
index 3dd9cd1..6891147 100644
--- a/org/default_regex.org
+++ b/org/default_regex.org
@@ -4,16 +4,15 @@
#+FILETAGS: :spine:regex:
#+AUTHOR: Ralph Amissah
#+EMAIL: [[mailto:ralph.amissah@gmail.com][ralph.amissah@gmail.com]]
-#+COPYRIGHT: Copyright (C) 2015 - 2019 Ralph Amissah
+#+COPYRIGHT: Copyright (C) 2015 - 2020 Ralph Amissah
#+LANGUAGE: en
-#+STARTUP: indent content hideblocks hidestars
-#+OPTIONS: H:3 num:nil toc:t \n:nil @:t ::t |:t ^:nil _:nil -:t f:t *:t <:t
-#+OPTIONS: TeX:t LaTeX:t skip:nil d:nil todo:t pri:nil tags:not-in-toc
-#+OPTIONS: author:nil email:nil creator:nil timestamp:nil
-#+PROPERTY: header-args :padline no :exports code :cache no :noweb yes
-#+EXPORT_SELECT_TAGS: export
-#+EXPORT_EXCLUDE_TAGS: noexport
-#+TAGS: assert(a) class(c) debug(d) mixin(m) spine(s) tangle(T) template(t) WEB(W) noexport(n)
+#+STARTUP: content hideblocks hidestars noindent entitiespretty
+#+PROPERTY: header-args :exports code
+#+PROPERTY: header-args+ :noweb yes
+#+PROPERTY: header-args+ :eval no
+#+PROPERTY: header-args+ :results no
+#+PROPERTY: header-args+ :cache no
+#+PROPERTY: header-args+ :padline no
[[./spine.org][spine]] [[./][org/]]
* meta ctRegex
@@ -25,13 +24,13 @@ http://dlang.org/phobos/std_regex.html
22 special characters used:
-#+BEGIN_SRC text
+#+BEGIN_SRC txt
【】〖〗┥┝┤├¤░┘┙┚┼┿╂┊┏┚┆■☼
#+END_SRC
** _module template_ :module:
-#+name: tangle_meta_rgx
+#+NAME: tangle_meta_rgx
#+BEGIN_SRC d :tangle "../src/doc_reform/meta/rgx.d"
/++
regex: regular expressions used in sisu document parser
@@ -48,7 +47,7 @@ static template spineRgxInit() {
** misc :misc:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ misc +/
// static true_dollar = ctRegex!(`\$`, "gm");
@@ -86,7 +85,7 @@ static numeric_col = ctRegex!(`^[ 0-9,.%$£
** comments :comment:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ comments +/
static comment = ctRegex!(`^%+ `);
@@ -94,7 +93,7 @@ static comment = ctRegex!(`^%+ `);
** config
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ header +/
#+END_SRC
@@ -102,7 +101,7 @@ static comment = ctRegex!(`^%+ `);
** native headers
*** native header :native:header:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ header +/
static variable_doc_title = ctRegex!(`@title`);
@@ -114,7 +113,7 @@ static yaml_config = ctRegex!(`^[a-z]+\s*:\s*
** heading & paragraph operators :paragraph:operator:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ heading & paragraph operators +/
static heading_a = ctRegex!(`^:?[A][~] `, "m");
@@ -145,7 +144,7 @@ static para_inline_link_anchor = ctRegex!(`\*[~](?P<ancho
** blocked markup
*** blocked markup curly & tic :block:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ blocked markup +/
static block_open = ctRegex!("^((code(?:[.][a-z][0-9a-z#+_]+)?|(?:poem|group|block|quote)(?:[.][a-z][0-9a-z_]+)?|table)(?:[(][ a-zA-Z0-9;:,]*[)])?[{][ ]*$)|^`{3} (code(?:[.][a-z][0-9a-z#+_]+)?|(?:poem|group|block|quote)(?:[.][a-z][0-9a-z_]+)?|table)(?:[(][ a-zA-Z0-9;:,]*[)])?|^[{]table[(](?:h;)?(?P<columns>(?:[ ,]+[0-9]+)+)[)][}]");
@@ -154,7 +153,7 @@ static block_poem_open = ctRegex!("^((poem(?:[(][
*** blocked markup tic :block:tic:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ blocked markup tics +/
static block_tic_code_open = ctRegex!("^`{3} code(?:[.](?P<syntax>[a-z][0-9a-z#+_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?");
@@ -168,7 +167,7 @@ static block_tic_close = ctRegex!("^(`{3})$","m")
*** blocked markup curly :block:curly:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ blocked markup curly +/
static block_curly_code_open = ctRegex!(`^(?:code(?:[.](?P<syntax>[a-z][0-9a-z_]+))?(?:[(](?P<attrib>[ a-zA-Z0-9;:,]*)[)])?[{][ ]*$)`);
@@ -189,14 +188,14 @@ static block_curly_table_special_markup = ctRegex!(`^[{]table[(](?
*** block sub-matches :block:
**** code
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
static code_numbering = ctRegex!(`(?P<number>\blinenumber\b|\bnumber\b|\blnr\b)`);
#+END_SRC
**** table
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
static table_head_instructions = ctRegex!(`(?:(?P<c_heading>h);)?(?:[ ]+c(?P<c_num>[0-9]):)?(?P<c_widths>(?:[, ]+[0-9]+[lr]?)+)`);
static table_col_widths_and_alignment = ctRegex!(`(?P<width>[0-9]+)(?P<align>[lr]?)`);
@@ -210,7 +209,7 @@ static table_col_separator_nl = ctRegex!(`[┊]$`, "mg")
** inline markup :inline:footnote:
*** footnotes & endnotes
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ inline markup footnotes endnotes +/
static inline_notes_curly_gen = ctRegex!(`~\{.+?\}~`, "m");
@@ -228,7 +227,7 @@ static note_ref = ctRegex!(`^\S+?noteref_(
*** links/ urls :inline:footnote:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
static webserv_url_doc_root = ctRegex!(`(?P<url>(?P<domain>https?:\/\/[^ /]+)\/(?P<path>\S*))`, "mg");
static smid_inline_url_generic = ctRegex!(`(?:^|[}(\[ ])(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)[a-zA-Z0-9_#]`, "mg");
@@ -241,7 +240,7 @@ static smid_inline_link_endnote_url_helper = ctRegex!(`\{~\^\s+(?P<co
*** images :images:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
static image = ctRegex!(`([a-zA-Z0-9._-]+?\.(?:png|gif|jpg))`, "mg");
static smid_image = ctRegex!(`(?P<pre>(?:^|[ ]|[^\S]?)[{┥](?:~\^\s+|\s*))(?P<image>[a-zA-Z0-9._-]+?\.(?:png|gif|jpg))(?P<post>(?:.*?)\s*[}┝](?:image|┤.*?├|(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?=[;:!,?.]?([ )\]]|$)))`, "mg");
@@ -254,7 +253,7 @@ static smid_image_delimit = ctRegex!(`(?P<pre>^|[ ]
*** inline markup book index :inline:bookindex:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ inline markup book index +/
static book_index = ctRegex!(`^=\{\s*(?P<bookindex>.+?)\}$`, "m");
@@ -265,7 +264,7 @@ static book_index_close = ctRegex!(`^(.*?)\}$`, "m
** switch
*** switch off auto-heading number
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
static auto_heading_numbering_lv1 = ctRegex!(`^1~`, "m");
static auto_heading_numbering_lv2 = ctRegex!(`^2~`, "m");
@@ -280,7 +279,7 @@ static auto_heading_numbering_off_lv4 = ctRegex!(`^4~\S*?-\s`, "m
** no object_number object :ocn:off:object:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ no object_number object +/
static object_number_off = ctRegex!(`~#[ ]*$`, "m");
@@ -291,7 +290,7 @@ static repeated_character_line_separator = ctRegex!(`^(?:[ ]*(?:(?:[.
** no object_number block :ocn:off:block:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ no object_number block +/
static object_number_off_block = ctRegex!(`^--~#$`);
@@ -302,7 +301,7 @@ static object_number_block_marks = ctRegex!(`^--[+~-]#$`);
** ignore outside code blocks :block:code:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ ignore outside code blocks +/
static skip_from_regular_parse = ctRegex!(`^(--[+~-]#|-[\\]{2}-|=[.\\]{2}=)$`);
@@ -310,7 +309,7 @@ static skip_from_regular_parse = ctRegex!(`^(--[+~-]#|-[\\]{2}-|=[.\\]{2}=)$`
** line & page breaks :break:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ line & page breaks +/
static break_string = ctRegex!(`』`);
@@ -318,7 +317,7 @@ static break_string = ctRegex!(`』`);
** biblio tags :biblio:tags:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ biblio tags +/
static biblio_tags = ctRegex!(`^(is|au|author_raw|author|author_arr|editor_raw|ed|editor_arr|ti|title|subtitle|fulltitle|lng|language|trans|src|jo|journal|in|vol|volume|edn|edition|yr|year|pl|place|pb|pub|publisher|url|pg|pages|note|short_name|id):\s+(.+)`);
@@ -327,7 +326,7 @@ static biblio_abbreviations = ctRegex!(`^(au|ed|ti|lng
** bookindex split :bookindex:split:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ bookindex split +/
static bi_main_terms_split = ctRegex!(`\s*;\s*`);
@@ -338,7 +337,7 @@ static bi_term_and_object_numbers_match = ctRegex!(`^(.+?)\+(\d+)`
** topic register split (document classify)
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
static topic_register_main_terms_split = ctRegex!(`\s*;\s*`);
static topic_register_main_term_plus_rest_split = ctRegex!(`\s*:\s*`);
@@ -348,7 +347,7 @@ static topic_register_multiple_sub_terms_split = ctRegex!(`␣([^|␣]+(?
** language codes :language:codes:
-#+name: meta_rgx
+#+NAME: meta_rgx
#+BEGIN_SRC d
/+ language codes +/
auto language_code_and_filename =
@@ -364,6 +363,7 @@ http://dlang.org/phobos/std_regex.html
** _module template_ :module:output:
+#+NAME: tangle_meta_rgx
#+BEGIN_SRC d :tangle "../src/doc_reform/io_out/rgx.d"
/++
regex: regular expressions used in sisu document parser
@@ -381,7 +381,7 @@ static template spineOutputRgxInit() {
** special characters
*** xhtml special characters
-#+name: sp_ch_xhtml_rgx
+#+NAME: sp_ch_xhtml_rgx
#+BEGIN_SRC d
static xhtml_ampersand = ctRegex!(`[&]`, "m"); // &amp;
static xhtml_quotation = ctRegex!(`["]`, "m"); // &quot;
@@ -392,7 +392,7 @@ static xhtml_line_break = ctRegex!(` [\\]{2}`, "m"); /
*** latex special characters
-#+name: sp_ch_xhtml_rgx
+#+NAME: sp_ch_xhtml_rgx
#+BEGIN_SRC d
static latex_special_char = ctRegex!(`([%${}_#&\\])`);
static latex_special_char_for_escape = ctRegex!(`([%${}_#\\])`);
@@ -409,7 +409,7 @@ static latex_clean_bookindex_linebreak = ctRegex!(`\s*\\\\\\\\\s*`, "
* 2. ctRegex defaults shared by meta & output (generic)
** misc generic
-#+name: prgmkup_rgx
+#+NAME: prgmkup_rgx
#+BEGIN_SRC d
static newline = ctRegex!("\n", "mg");
static space = ctRegex!(`[ ]`, "mg");
@@ -420,7 +420,7 @@ static nbsp_char = ctRegex!(`░`, "mg");
** filename (& path) (including insert file) :insert:file:path:filename:
-#+name: prgmkup_rgx
+#+NAME: prgmkup_rgx
#+BEGIN_SRC d
static src_pth_sst_or_ssm = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.](?P<extension>ss[tm]))$`);
static src_pth_pod_sst_or_ssm = ctRegex!(`^(?P<podpath>[/]?(?:[a-zA-Z0-9._-]+/)*)media/text/[a-z]{2}/(?P<filename>[a-zA-Z0-9][a-zA-Z0-9._-]*?[.]ss[tm])$`);
@@ -441,7 +441,7 @@ static src_formalised_file_path_parts = ctRegex!(`(?P<pth>(?:[/a
*** inline breaks
-#+name: prgmkup_rgx
+#+NAME: prgmkup_rgx
#+BEGIN_SRC d
/+ line breaks +/
static br_empty_line = ctRegex!(`\n[ ]*\n`, "mg");
@@ -452,7 +452,7 @@ static br_nl = ctRegex!(`┙`, "mg");
*** inline (internal program) markup footnotes endnotes :inline:footnote:
-#+name: prgmkup_rgx
+#+NAME: prgmkup_rgx
#+BEGIN_SRC d
/+ inline markup footnotes endnotes +/
static inline_notes_al = ctRegex!(`【(?:[*+]\s+|\s*)(.+?)】`, "mg");
@@ -472,7 +472,7 @@ static inline_text_and_note_al_ = ctRegex!(`(.+?(?:【[*+]
*** inline links
-#+name: prgmkup_rgx
+#+NAME: prgmkup_rgx
#+BEGIN_SRC d
/+ inline markup links +/
static inline_image = ctRegex!(`(?P<pre>┥)☼(?P<imginf>(?P<img>[a-zA-Z0-9._-]+?\.(?:jpg|gif|png)),w(?P<width>\d+)h(?P<height>\d+))\s*(?P<post>.*?┝┤.*?├)`, "mg");
@@ -499,7 +499,7 @@ static quotation_mark_sql_insert_delimiter = ctRegex!("[']", "mg");
*** inline markup font face mod :inline:font:face:
-#+name: prgmkup_rgx
+#+NAME: prgmkup_rgx
#+BEGIN_SRC d
/+ inline markup font face mod +/
static inline_mark_emphasis = ctRegex!(`(?P<mark>[*])\{(?P<text>.+?)\}[*]`, "mg");
@@ -514,7 +514,7 @@ static inline_mark_mono = ctRegex!(`(?P<mark>[#])\{(
static inline_mark_cite = ctRegex!(`(?P<mark>["])\{(?P<text>.+?)\}["]`, "mg");
#+END_SRC
-#+name: prgmkup_rgx
+#+NAME: prgmkup_rgx
#+BEGIN_SRC d
static inline_faces_line = ctRegex!(`^[*!/_]_ (?P<text>.+?)((?: [\\]{2}|[~]#){0,2}$)`);
static inline_emphasis_line = ctRegex!(`^\*_ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
@@ -523,7 +523,7 @@ static inline_italics_line = ctRegex!(`^/_ (?P<text>.
static inline_underscore_line = ctRegex!(`^__ (?P<text>.+?)(?P<tail>(?: [\\]{2}|[~]#){0,2}$)`);
#+END_SRC
-#+name: prgmkup_rgx
+#+NAME: prgmkup_rgx
#+BEGIN_SRC d
/+ inline markup font face mod +/
static inline_emphasis = ctRegex!(`[*]┨(?P<text>.+?)┣[*]`, "mg");
@@ -542,7 +542,7 @@ static inline_fontface_clean = ctRegex!(`[*!_/^,+■‖
*** table related
-#+name: prgmkup_rgx
+#+NAME: prgmkup_rgx
#+BEGIN_SRC d
/+ table delimiters +/
static table_delimiter_col = ctRegex!("[ ]*[┊][ ]*", "mg");