dwc_agent 3.0.5.0 → 3.0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3970c5d18e841f3812830b0df8f45341219da6a11210330dd41f65fb65e6b6af
-  data.tar.gz: 648a0ca6384df1dc47dc1a11883a448095f53c901828d04cdc116dd47974a370
+  metadata.gz: 69985a64afbcf03bbb14df6e00f85cfbd1470846a289aa490e1b62a41986285d
+  data.tar.gz: b2158f59c97be96d2217a9c8dbf86fce3d256a649485d6d29dc510069c144f04
 SHA512:
-  metadata.gz: 8469ecdedc125f6a4101186d7af8d22fdd61b08877a73d38c374b5abbe157ce076da3a511966cff66cc9587cedeb56deb0291ce428c5f4dbbcff4e44db8a7f49
-  data.tar.gz: b315bd0463332a66aa1aa530daedc4d46a9ed96ba02976e65ac51e0e5ff0a1d4c1b18be02db5805ec77b2215aa1480052b5f6dc9bb81c36b0016642808e57ed3
+  metadata.gz: 2fd0d7089120d60ac306758a5a8b2efbd3a31d5174fe1e16cb4a627df73cbcb364e622c0cc0de05dcbadaaa775895aa2d89e57739b447679b2ac1fcce63acd60
+  data.tar.gz: 84398f5548ef552f4e86b05b3f1bc11e2a67355b283ef74986fc5061fa7e77bce894401ff88cd9dae72103bd01520c2e53896ed0d5d34aae0f38d48bbee8ae0e

data/lib/dwc_agent/constants.rb

@@ -127,7 +127,8 @@ module DwcAgent
     \:?\s*(?i:exch)(\b|\z)|
     \s+de\s*$|
     \.{2,}$|
-    \[|\]
+    \[|\]|
+    [^[:alnum:][:blank:][:punct:][∣´|ǀ∣｜│`~$^+|<>]]      # Removes emojis from string
   }x
 
   SPLIT_BY = %r{
@@ -144,6 +145,7 @@ module DwcAgent
     \b(?i:confirmada)(\s+por)?\s*\b|
     \b(?i:checked?(\s+by)?)\s*\b|
     \b(?i:det\.?(\s+by)?)\s*\b|
+    \b(?i:(donated)?\s*by)\s+|
     \b(?i:dupl?\.?(\s+by)?|duplicate(\s+by)?)\s*\b|
     \b(?i:ex\.?(\s+by)?|examined(\s+by)?)\s*\b|
     \b(?i:in?dentified(\s+by)?)\s*\b|
@@ -156,8 +158,7 @@ module DwcAgent
     \b(?i:stet)\s*\b|
     \b(?i:then(\s+by)?)\s+|
     \b(?i:veri?f?\.?\:?(\s+by)?|v(e|é)rifi(e|é)d?(\s+by)?)\s*\b|
-    \b(?i:via|from)\s*\b|
-    \b(?i:(donated)?\s*by)\s+
+    \b(?i:via|from)\s*\b
   }x
 
   CHAR_SUBS = {
@@ -202,14 +203,15 @@ module DwcAgent
   }
 
   SEPARATORS = {
+    "^([A-Z]{1}\\.\\s*[[:alpha:]]{1,}),\\s*?([A-Z.]{1,})$" => "\\1 \\2",
     "^(\\S{4,},\\s+(?:\\S\\.\\s*){1,})\\s+(\\S{4,},\\s+(?:\\S\.\\s*){1,})$" => "\\1 | \\2",
     "(\\S{1}\\.)([[:alpha:]]{2,})" => "\\1 \\2",
     "([[:alpha:]]*),?\\s+(.*)\\s+(van|von)$" => "\\3 \\1, \\2",
     "^([A-Z.\\s]+)\\s+(?:and|&|et|e)\\s+([A-Z.\\s]+)\\s+([[:alpha:]]{2,})\\s+([[:alpha:]]{2,})$" => "\\1 \\4 | \\2 \\3 \\4",
     "^([A-Z.\\s]+)\\s+(?:and|&|et|e)\\s+([A-Z.\\s]+)\\s+([[:alpha:]]{2,})(.*)$" => "\\1 \\3 | \\2 \\3 | \\4",
-    "^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?[,&]\\s*?([A-Z][[:alpha:]]{2,})$" => "\\1 | \\2 | \\3",
-    "^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?[,&]\\s*?([A-Z][[:alpha:]]{3,})$" => "\\1 | \\2 | \\3 | \\4",
-    "^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?[,&]\\s*?([A-Z][[:alpha:]]{3,})$" => "\\1 | \\2 | \\3 | \\4 | \\5"
+    "^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?(?i:and|&|et|e|,)\\s+([A-Z][[:alpha:]]{2,})$" => "\\1 | \\2 | \\3",
+    "^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?(?i:and|&|et|e|,)\\s+([A-Z][[:alpha:]]{3,})$" => "\\1 | \\2 | \\3 | \\4",
+    "^([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,}),\\s*?([A-Z][[:alpha:]]{2,})\\s*?(?i:and|&|et|e|,)\\s+([A-Z][[:alpha:]]{3,})$" => "\\1 | \\2 | \\3 | \\4 | \\5"
   }
 
   BLACKLIST = %r{

data/lib/dwc_agent/version.rb

@@ -4,7 +4,7 @@ module DwcAgent
 
     MAJOR = 3
     MINOR = 0
-    PATCH = 5
+    PATCH = 6
     BUILD = 0
 
     def self.version

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: dwc_agent
 version: !ruby/object:Gem::Version
-  version: 3.0.5.0
+  version: 3.0.6.0
 platform: ruby
 authors:
 - David P. Shorthouse
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-06-26 00:00:00.000000000 Z
+date: 2023-06-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: namae