From e973365c4b74be2b2cff9be970ccba5928dbe368 Mon Sep 17 00:00:00 2001
From: Ralph Amissah <ralph.amissah@gmail.com>
Date: Wed, 22 May 2019 10:50:33 -0400
Subject: 0.7.3 start to look at document harvest (initial stub)

---
 org/default_regex.org | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

(limited to 'org/default_regex.org')

diff --git a/org/default_regex.org b/org/default_regex.org
index 2958027..6d17f0c 100644
--- a/org/default_regex.org
+++ b/org/default_regex.org
@@ -51,6 +51,7 @@ static template DocReformRgxInit() {
 #+BEGIN_SRC d
 /+ misc +/
 static true_dollar                                    = ctRegex!(`\$`, "gm");
+static sep                                            = ctRegex!(`␣`, "gm");
 static flag_action                                    = ctRegex!(`^(--[a-z][a-z0-9-]+)$`);
 static flag_action_str                                = ctRegex!(` (--[a-z][a-z0-9-]+)`);
 static within_quotes                                  = ctRegex!(`"(.+?)"`, "m");
@@ -106,7 +107,7 @@ static make_simple_substitutions_d                    = ctRegex!(`(?P<substituti
 /+ header +/
 static variable_doc_title                             = ctRegex!(`@title`);
 static variable_doc_author                            = ctRegex!(`@author|@creator`);
-static raw_author_munge                               = ctRegex!(`(\S.+?),\s+(.+)`,"i");
+static raw_author_munge                               = ctRegex!(`(?P<last>\S.+?),\s+(?P<first>.+)`,"i");
 static toml_header_meta_title                         = ctRegex!(`^\s*(title\s*=\s*"|\[title\])`, "m");
 #+END_SRC
 
@@ -368,6 +369,16 @@ static bi_sub_terms_plus_object_number_offset_split   = ctRegex!(`\s*\|\s*`);
 static bi_term_and_object_numbers_match               = ctRegex!(`^(.+?)\+(\d+)`);
 #+END_SRC
 
+** topic register split (document classify)
+
+#+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*`);
+static topic_register_sub_terms_split                 = ctRegex!(`\s*\|\s*`);
+static topic_register_multiple_sub_terms_split        = ctRegex!(`␣([^|␣]+(?:\|[^|␣]+)+)`);
+#+END_SRC
+
 ** language codes                                           :language:codes:
 
 #+name: meta_rgx
-- 
cgit v1.2.3