Extract toc types

PopulateTools · Nov 21, 2024 · 77dd836 · 77dd836
1 parent 3c9a0cd
commit 77dd836
Show file tree

Hide file tree

Showing 3 changed files with 39 additions and 16 deletions.
diff --git a/lib/section_extractor.rb b/lib/section_extractor.rb
@@ -10,4 +10,5 @@ class Error < StandardError; end
 require_relative "section_extractor/toc_item"
 require_relative "section_extractor/toc_parser"
 require_relative "section_extractor/toc"
+require_relative "section_extractor/toc_types"
 require_relative "section_extractor/version"
diff --git a/lib/section_extractor/toc_parser.rb b/lib/section_extractor/toc_parser.rb
@@ -2,21 +2,7 @@
 
 module SectionExtractor
   class TocParser
-    ROMAN_SERIES = %w[I II III IV V VI VII VIII IX X XI XII XIII XIV XV].freeze
-    ALPHA_SERIES = ("a".."z").to_a
     MAX_TOC_ITEM_SIZE = 60
-    RE_NUMERIC = /\n(\d+(?:\.\d+)*\.?-?\s+[^\n]+)\n/m
-    RE_NUMERIC_WITH_CLAUSE = /\n((?:Cláusula\s+)(\d+(?:\.\d+)*\.?-?\s+[^\n]+))\n/m
-    RE_ROMAN = /\n((?:IX|IV|V?I{1,3}|VI{1,3}|X{1,3}V?I{0,3})\s?\.?-?\s+[^\n]+)\n/mi
-    RE_ROMAN_WITH_TITLE = /\n((?:ANEXO|CAPITULO|CAPÍTULO|TÍTULO|TITULO)\s+(?:IX|IV|V?I{1,3}|VI{1,3}|X{1,3}V?I{0,3})[.-]*\s+[^\n]+)\n/mi
-    RE_ALPHA = /\n([a-zA-Z][).-]+\s+[^\n]+)\n/m
-    REGEXES_WITH_TYPES = {
-      numeric: RE_NUMERIC,
-      numeric_with_clause: RE_NUMERIC_WITH_CLAUSE,
-      roman: RE_ROMAN,
-      roman_with_title: RE_ROMAN_WITH_TITLE,
-      alpha: RE_ALPHA
-    }
 
     attr_reader :content, :tocs
 
@@ -26,8 +12,8 @@ def initialize(content)
     end
 
     def call
-      REGEXES_WITH_TYPES.map do |type, re|
-        content.scan(re).each do |match|
+      TocTypes.all.map do |type, options|
+        content.scan(options[:regexp]).each do |match|
           toc_item_title = match.first.strip.gsub(/\n/, "").gsub(/\s+/, " ")
           toc_item_title = toc_item_title.split(":").first.strip if toc_item_title.include?(":")
           # Skip the TOC item if it has more than 5 dots

diff --git a/lib/section_extractor/toc_types.rb b/lib/section_extractor/toc_types.rb
@@ -0,0 +1,36 @@
+# frozen_string_literal: true
+
+module SectionExtractor
+  class TocTypes
+    RE_NUMERIC = /\n(\d+(?:\.\d+)*\.?-?\s+[^\n]+)\n/m
+    RE_NUMERIC_WITH_CLAUSE = /\n((?:Cláusula\s+)(\d+(?:\.\d+)*\.?-?\s+[^\n]+))\n/m
+    RE_ROMAN = /\n((?:IX|IV|V?I{1,3}|VI{1,3}|X{1,3}V?I{0,3})\s?\.?-?\s+[^\n]+)\n/mi
+    RE_ROMAN_WITH_TITLE = /\n((?:ANEXO|CAPITULO|CAPÍTULO|TÍTULO|TITULO)\s+(?:IX|IV|V?I{1,3}|VI{1,3}|X{1,3}V?I{0,3})[.-]*\s+[^\n]+)\n/mi
+    RE_ALPHA = /\n([a-zA-Z][).-]+\s+[^\n]+)\n/m
+
+    def self.all
+      {
+        numeric: {
+          regexp: RE_NUMERIC,
+          first_value: 1
+        },
+        numeric_with_clause: {
+          regexp: RE_NUMERIC_WITH_CLAUSE,
+          first_value: 1
+        },
+        roman: {
+          regexp: RE_ROMAN,
+          first_value: "I"
+        },
+        roman_with_title: {
+          regexp: RE_ROMAN_WITH_TITLE,
+          first_value: "I"
+        },
+        alpha: {
+          regexp: RE_ALPHA,
+          first_value: "a"
+        }
+      }
+    end
+  end
+end