From a263d67a5dfb5fad70059f63c1029f9174bf7ff0 Mon Sep 17 00:00:00 2001
From: Ralph Amissah <ralph@amissah.com>
Date: Mon, 30 Apr 2018 21:05:13 -0400
Subject: link url matching

- smid: sisu markup identify
- inline_link_markup_regular matches series of
  marked up urls, e.g.
  { link txt }http://url, { link txt }http://url
---
 org/default_regex.org | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

(limited to 'org/default_regex.org')

diff --git a/org/default_regex.org b/org/default_regex.org
index e824577..5b759b0 100644
--- a/org/default_regex.org
+++ b/org/default_regex.org
@@ -225,7 +225,8 @@ static table_col_separator                            = ctRegex!(`┊`);
 static table_col_separator_nl                         = ctRegex!(`[┊]$`, "mg");
 #+END_SRC
 
-** inline markup footnotes endnotes                        :inline:footnote:
+** inline markup                                           :inline:footnote:
+*** footnotes & endnotes
 
 #+name: meta_rgx
 #+BEGIN_SRC d
@@ -255,12 +256,12 @@ static note_ref                                       = ctRegex!(`^\S+?noteref_(
 
 #+name: meta_rgx
 #+BEGIN_SRC d
-static inline_url_generic                              = ctRegex!(`(?:^|[}(\[ ])(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)[a-zA-Z0-9_#]`, "mg");
-static inline_url                                      = ctRegex!(`((?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)[a-zA-Z0-9_]\S*)`, "mg");
-static inline_link_naked_url                           = ctRegex!(`(?P<before>^|[ ])(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤)\S+?)(?P<after>[.,;:?!'"]?(?:[ ]|$))`, "mg");
-static inline_link_markup_regular                      = ctRegex!(`(?P<before>^|[ ])\{\s*(?P<content>.+?)\s*\}(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?P<after>(?:[,;:? ]|[!.]?(?:[ ]|$)))`, "mg");
-static inline_link_endnote_url_helper_punctuated       = ctRegex!(`\{~\^\s+(?P<content>.+?)\}(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?P<after>[.,;:?!]?(?:[ ]|$))`, "mg");
-static inline_link_endnote_url_helper                  = ctRegex!(`\{~\^\s+(?P<content>.+?)\}(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+)`, "mg");
+static smid_inline_url_generic                        = ctRegex!(`(?:^|[}(\[ ])(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)[a-zA-Z0-9_#]`, "mg");
+static smid_inline_url                                = ctRegex!(`((?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)[a-zA-Z0-9_]\S*)`, "mg");
+static smid_inline_link_naked_url                     = ctRegex!(`(?P<pre>^|[ ])(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤)\S+?)(?P<post>[.,;:?!'"]?(?:[ ]|$))`, "mg"); // issue with #link #32
+static smid_inline_link_markup_regular                = ctRegex!(`(?P<pre>^|[ ]|[^\S]?)\{\s*(?P<content>.+?)\s*\}(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?P<post>[;:!,?.]?(?:[ )\]]|$))`, "mg"); // NEXT
+static smid_inline_link_endnote_url_helper_punctuated = ctRegex!(`\{~\^\s+(?P<content>.+?)\}(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+?)(?P<after>[.,;:?!]?(?:[ ]|$))`, "mg");
+static smid_inline_link_endnote_url_helper            = ctRegex!(`\{~\^\s+(?P<content>.+?)\}(?P<link>(?:(?:https?|git):\/\/|¤?\.\.\/|¤?\.\/|¤|#)\S+)`, "mg");
 #+END_SRC
 
 *** images                                                         :images:
@@ -392,7 +393,7 @@ static template SiSUoutputRgxInit() {
 #+name: sp_ch_xhtml_rgx
 #+BEGIN_SRC d
 static xhtml_ampersand                            = ctRegex!(`[&]`);      // &amp;
-static xhtml_quotation                            = ctRegex!(`[&]`);      // &quot;
+static xhtml_quotation                            = ctRegex!(`["]`);      // &quot;
 static xhtml_less_than                            = ctRegex!(`[<]`);      // &lt;
 static xhtml_greater_than                         = ctRegex!(`[>]`);      // &gt;
 static xhtml_line_break                           = ctRegex!(` [\\]{2}`); // <br />
-- 
cgit v1.2.3