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)

---
 src/doc_reform/meta/rgx.d | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'src/doc_reform/meta/rgx.d')

diff --git a/src/doc_reform/meta/rgx.d b/src/doc_reform/meta/rgx.d
index 373400f..544b432 100644
--- a/src/doc_reform/meta/rgx.d
+++ b/src/doc_reform/meta/rgx.d
@@ -7,6 +7,7 @@ static template DocReformRgxInit() {
   static struct Rgx {
     /+ 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");
@@ -43,7 +44,7 @@ static template DocReformRgxInit() {
     /+ 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");
     /+ heading & paragraph operators +/
     static heading_a                                      = ctRegex!(`^:?[A][~] `, "m");
@@ -191,6 +192,10 @@ static template DocReformRgxInit() {
     static bi_main_term_plus_rest_split                   = ctRegex!(`\s*:\s*`);
     static bi_sub_terms_plus_object_number_offset_split   = ctRegex!(`\s*\|\s*`);
     static bi_term_and_object_numbers_match               = ctRegex!(`^(.+?)\+(\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!(`␣([^|␣]+(?:\|[^|␣]+)+)`);
     /+ language codes +/
     auto language_codes                                    =
        ctRegex!("(am|bg|bn|br|ca|cs|cy|da|de|el|en|eo|es|et|eu|fi|fr|ga|gl|he|hi|hr|hy|ia|is|it|ja|ko|la|lo|lt|lv|ml|mr|nl|no|nn|oc|pl|pt|pt_BR|ro|ru|sa|se|sk|sl|sq|sr|sv|ta|te|th|tk|tr|uk|ur|vi|zh)");
-- 
cgit v1.2.3