aboutsummaryrefslogtreecommitdiffhomepage
path: root/org/default_regex.org
diff options
context:
space:
mode:
authorRalph Amissah <ralph@amissah.com>2017-05-06 11:33:10 -0400
committerRalph Amissah <ralph@amissah.com>2019-04-10 15:14:14 -0400
commit7a73aa10276b0c1151500d26b194336b56af7aba (patch)
treee267901f73375393cc429c5c17ce661216de111a /org/default_regex.org
parentxmls work particularly with epub output (diff)
Diffstat (limited to 'org/default_regex.org')
-rw-r--r--org/default_regex.org29
1 files changed, 14 insertions, 15 deletions
diff --git a/org/default_regex.org b/org/default_regex.org
index baeca25..01aa763 100644
--- a/org/default_regex.org
+++ b/org/default_regex.org
@@ -62,8 +62,8 @@ static line_delimiter_ws_strip = ctRegex!("[ ]*\n[ ]*");
static para_delimiter = ctRegex!("\n[ ]*\n+");
static table_col_delimiter = ctRegex!("[ ]*\n+", "mg");
static table_row_delimiter = ctRegex!("\n[ ]*\n+", "mg");
-static table_row_delimiter_special = ctRegex!("[ ]*\n", "mg"); //
-static table_col_delimiter_special = ctRegex!("[ ]*[|][ ]*", "mg"); //
+static table_row_delimiter_special = ctRegex!("[ ]*\n", "mg");
+static table_col_delimiter_special = ctRegex!("[ ]*[|][ ]*", "mg");
static levels_markup = ctRegex!(`^[A-D1-4]$`);
static levels_numbered = ctRegex!(`^[0-9]$`);
static levels_numbered_headings = ctRegex!(`^[0-7]$`);
@@ -128,12 +128,11 @@ static heading_seg_and_above = ctRegex!(`^:?([A-D1])[~]
static heading_marker = ctRegex!(`^:?([A-D1-4])[~]`);
static heading_anchor_tag = ctRegex!(`^:?[A-D1-4][~]([a-z0-9_.-]+) `,"i");
static heading_identify_anchor_tag = ctRegex!(`^:?[A-D1-4][~]\s+(?:(?:(?:chapter|article|section|clause)\s+[0-9.]+)|(?:[0-9]+))`,"i");
- // unless dob.obj =~/^:?[A-D1-4]~\s+(?:|(?:chapter|article|section|clause)\s+)([0-9.]+)/i
static heading_extract_named_anchor_tag = ctRegex!(`^:?[A-D1-4][~]\s+(chapter|article|section|clause)\s+((?:[0-9]+.)*[0-9]+)(?:[.:;, ]|$)`,"i");
static heading_extract_unnamed_anchor_tag = ctRegex!(`^:?[A-D1-4][~]\s+((?:[0-9]+.)*[0-9]+)(?:[.:;, ]|$)`);
static heading_marker_missing_tag = ctRegex!(`^:?([A-D1-4])[~] `);
static heading_title = ctRegex!(`^:?[A-D1-4][~][a-z0-9_.-]*[?]?\s+(.+?)$`);
-static heading_all = ctRegex!(`^:?([A-D1-4])[~]([a-z0-9_.-]*[?]?)\s+(.+?)$`); // test, particularly [2] name/hashtag which may or may not be, does this affect title [3]
+static heading_all = ctRegex!(`^:?([A-D1-4])[~]([a-z0-9_.-]*[?]?)\s+(.+?)$`);
static heading_backmatter = ctRegex!(`^:?1[~][!](glossary|bibliography|biblio|blurb)\s+`,"i");
static heading_biblio = ctRegex!(`^:?(1)[~][!](biblio(?:graphy)?|references?)`);
static heading_glossary = ctRegex!(`^:?(1)[~][!](glossary)`);
@@ -191,7 +190,7 @@ static block_curly_quote_open = ctRegex!(`^(quote[{].*?$
static block_curly_quote_close = ctRegex!(`^([}]quote)`);
static block_curly_table_open = ctRegex!(`^table[{](.*)`);
static block_curly_table_close = ctRegex!(`^([}]table)`);
-static block_curly_table_special_markup = ctRegex!(`^[{]table((~h)?(?P<columns>(?:[ ]+[0-9]+;)+))[}]`, "mg"); // sepcial table block markup
+static block_curly_table_special_markup = ctRegex!(`^[{]table((~h)?(?P<columns>(?:[ ]+[0-9]+;)+))[}]`, "mg");
#+END_SRC
*** block sub-matches :block:curly:
@@ -225,9 +224,9 @@ static inline_text_and_note_square_sp = ctRegex!(`(.+?)~\[[*+]+\
static inline_text_and_note_square = ctRegex!(`(.+?)~\[\s*(.+?)\]~`, "mg");
static inline_note_square_delimiters = ctRegex!(`(~\[\s*)(.+?)(\]~)`, "mg");
static inline_curly_delimiter_open_regular = ctRegex!(`~\{\s*`, "m");
-static inline_curly_delimiter_open_symbol_star = ctRegex!(`~\{[*]\s`, "m"); //
-static inline_curly_delimiter_open_symbol_plus = ctRegex!(`~\{[+]\s`, "m"); //
-static inline_curly_delimiter_open_star_or_plus = ctRegex!(`~\{[+*]`, "m"); //
+static inline_curly_delimiter_open_symbol_star = ctRegex!(`~\{[*]\s`, "m");
+static inline_curly_delimiter_open_symbol_plus = ctRegex!(`~\{[+]\s`, "m");
+static inline_curly_delimiter_open_star_or_plus = ctRegex!(`~\{[+*]`, "m");
static inline_curly_delimiter_close_regular = ctRegex!(`\s*\}~`, "m");
static inline_text_and_note_curly = ctRegex!(`(?P<text>.+?)(?:(?:[~])[{][*+ ]*)(?P<note>.+?)(?:[}][~])`, "mg");
static note_ref = ctRegex!(`^\S+?noteref_([0-9]+)`, "mg"); // {^{73.}^}#noteref_73
@@ -259,7 +258,7 @@ static image = ctRegex!(`([a-zA-Z0-9._
/+ inline markup book index +/
static book_index = ctRegex!(`^=\{\s*(.+?)\}$`, "m");
static book_index_open = ctRegex!(`^=\{\s*([^}]+?)$`);
-static book_index_close = ctRegex!(`^(.*?)\}$`, "m"); // strip
+static book_index_close = ctRegex!(`^(.*?)\}$`, "m");
#+END_SRC
** no obj_cite_number object :ocn:off:object:
@@ -288,7 +287,7 @@ static obj_cite_number_block_marks = ctRegex!(`^--[+~-]#$`);
#+name: ao_rgx
#+BEGIN_SRC d
/+ ignore outside code blocks +/
-static skip_from_regular_parse = ctRegex!(`^(--[+~-]#|-[\\]{2}-|=[.\\]{2}=)$`); // not structural info
+static skip_from_regular_parse = ctRegex!(`^(--[+~-]#|-[\\]{2}-|=[.\\]{2}=)$`);
#+END_SRC
** line & page breaks :break:
@@ -387,7 +386,7 @@ static newline = ctRegex!("\n", "mg");
static strip_br = ctRegex!("^<br>\n|<br>\n*$");
static space = ctRegex!(`[ ]`, "mg");
static spaces_line_start = ctRegex!(`^(?P<opening_spaces>[ ]+)`, "mg");
-static spaces_multiple = ctRegex!(`(?P<multiple_spaces>[ ]{2,})`, "mg"); // could be issues for endnotes
+static spaces_multiple = ctRegex!(`(?P<multiple_spaces>[ ]{2,})`, "mg");
static two_spaces = ctRegex!(`[ ]{2}`, "mg");
static nbsp_char = ctRegex!(`░`, "mg");
static nbsp_chars_line_start = ctRegex!(`^░+`, "mg");
@@ -395,7 +394,7 @@ static nbsp_and_space = ctRegex!(`&nbsp;[ ]`, "m
static nbsp_char_and_space = ctRegex!(`░[ ]`, "mg");
#+END_SRC
-** filename (and path) matching (including markup insert file) :insert:file:path:filename:
+** filename (& path) (including insert file) :insert:file:path:filename:
#+name: prgmkup_rgx
#+BEGIN_SRC d
@@ -443,7 +442,7 @@ static inline_seg_link = ctRegex!(`(¤)(?:.+?)\.f
static mark_internal_site_lnk = ctRegex!(`¤`, "mg");
#+END_SRC
-*** inline markup font face mod :inline:font:face:
+*** inline markup font face mod :inline:font:face:
#+name: prgmkup_rgx
#+BEGIN_SRC d
@@ -471,6 +470,6 @@ static inline_underscore_line = ctRegex!(`^__ (?P<text>.
#+name: prgmkup_rgx
#+BEGIN_SRC d
/+ table delimiters +/
-static table_delimiter_col = ctRegex!("[ ]*[┊][ ]*", "mg"); //
-static table_delimiter_row = ctRegex!("[ ]*\n", "mg"); //
+static table_delimiter_col = ctRegex!("[ ]*[┊][ ]*", "mg");
+static table_delimiter_row = ctRegex!("[ ]*\n", "mg");
#+END_SRC