municipitaly2 2.0.2 → 2.0.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 224c12115ea80572b0572b38215e5d4253b3a8a857f01cda384a32239707be13
-  data.tar.gz: cdcb4d301ba9420fcc4b4c7800bbb2cbb92fd37cd1e9436db0a81a2de1f989a7
+  metadata.gz: 6d902371314d1cd9ee768b61f9ea0b3b2068725802993273fc369a9e8e155ae9
+  data.tar.gz: 3791df596b257073b1f9607ef574c102ec3bf398480f4a5982be6f2bcdbd7926
 SHA512:
-  metadata.gz: 472c21524089a08d167ab736fd7fd22274b66efccf1cf0e669da133c1cd7356607771999416a78588f6f13744b25ac6da5f290392b828f2fafdd10d838c27574
-  data.tar.gz: 303c00313760f6572b63683857fc998828b5e972b5d28f76c71800cf6355c87223830290a373df115e3078a1892a5450aa4301452ba550927d8bd4c976d57061
+  metadata.gz: d056647d30265de06c3e6750e8ecb3009de4c3cd03e771764fdc8b2592774478fa61988cbc7ea66e740fee3e9ec19258c6b2c05c2321e3deb78f8ef3221fee62
+  data.tar.gz: f6e9d07aaf5089cd5eb30d677b6360bd628083a02362f32403abfa1996a97eae6cf66067ac8345fcb2c6e857033958f466b7ed8b860d5aeafef156a18670f92d

data/CHANGELOG.md

@@ -5,6 +5,17 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [2.0.4] - 2025-09-09
+
+- Updated database
+- Updated gems
+- Improved search municipalities results order
+
+## [2.0.3] - 2024-12-17
+
+- Search region by its name: `Municipitaly::Search.region_from_name('a region')`
+- Fixed and tested specs
+
 ## [2.0.2] - 2024-12-13
 
 - Added `csv` to spec as advised for ruby `3.4.0` onward

data/Gemfile

@@ -4,3 +4,9 @@ source 'https://rubygems.org'
 
 # Specify your gem's dependencies in fitbark.gemspec
 gemspec
+
+gem 'bundler', '~> 2.7'
+gem 'rake', '~> 13.3'
+gem 'rspec', '~> 3.13'
+gem 'rubocop', '~> 1.80'
+gem 'simplecov', '~> 0.22'

data/Gemfile.lock

@@ -1,73 +1,77 @@
 PATH
   remote: .
   specs:
-    municipitaly2 (2.0.0)
+    municipitaly2 (2.0.4)
+      csv (~> 3.3.5)
 
 GEM
   remote: https://rubygems.org/
   specs:
-    ast (2.4.2)
-    diff-lcs (1.5.1)
-    docile (1.4.0)
-    json (2.7.2)
-    language_server-protocol (3.17.0.3)
-    parallel (1.25.1)
-    parser (3.3.4.0)
+    ast (2.4.3)
+    csv (3.3.5)
+    diff-lcs (1.6.2)
+    docile (1.4.1)
+    json (2.13.2)
+    language_server-protocol (3.17.0.5)
+    lint_roller (1.1.0)
+    parallel (1.27.0)
+    parser (3.3.9.0)
       ast (~> 2.4.1)
       racc
-    racc (1.8.0)
+    prism (1.4.0)
+    racc (1.8.1)
     rainbow (3.1.1)
-    rake (13.2.1)
-    regexp_parser (2.9.2)
-    rexml (3.3.2)
-      strscan
-    rspec (3.13.0)
+    rake (13.3.0)
+    regexp_parser (2.11.2)
+    rspec (3.13.1)
       rspec-core (~> 3.13.0)
       rspec-expectations (~> 3.13.0)
       rspec-mocks (~> 3.13.0)
-    rspec-core (3.13.0)
+    rspec-core (3.13.5)
       rspec-support (~> 3.13.0)
-    rspec-expectations (3.13.1)
+    rspec-expectations (3.13.5)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.13.0)
-    rspec-mocks (3.13.1)
+    rspec-mocks (3.13.5)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.13.0)
-    rspec-support (3.13.1)
-    rubocop (1.64.1)
+    rspec-support (3.13.5)
+    rubocop (1.80.2)
       json (~> 2.3)
-      language_server-protocol (>= 3.17.0)
+      language_server-protocol (~> 3.17.0.2)
+      lint_roller (~> 1.1.0)
       parallel (~> 1.10)
       parser (>= 3.3.0.2)
       rainbow (>= 2.2.2, < 4.0)
-      regexp_parser (>= 1.8, < 3.0)
-      rexml (>= 3.2.5, < 4.0)
-      rubocop-ast (>= 1.31.1, < 2.0)
+      regexp_parser (>= 2.9.3, < 3.0)
+      rubocop-ast (>= 1.46.0, < 2.0)
       ruby-progressbar (~> 1.7)
-      unicode-display_width (>= 2.4.0, < 3.0)
-    rubocop-ast (1.31.3)
-      parser (>= 3.3.1.0)
+      unicode-display_width (>= 2.4.0, < 4.0)
+    rubocop-ast (1.46.0)
+      parser (>= 3.3.7.2)
+      prism (~> 1.4)
     ruby-progressbar (1.13.0)
     simplecov (0.22.0)
       docile (~> 1.1)
       simplecov-html (~> 0.11)
       simplecov_json_formatter (~> 0.1)
-    simplecov-html (0.12.3)
+    simplecov-html (0.13.2)
     simplecov_json_formatter (0.1.4)
-    strscan (3.1.0)
-    unicode-display_width (2.5.0)
+    unicode-display_width (3.1.5)
+      unicode-emoji (~> 4.0, >= 4.0.4)
+    unicode-emoji (4.0.4)
 
 PLATFORMS
   ruby
   x86_64-linux
 
 DEPENDENCIES
-  bundler (~> 2.5.11)
+  bundler (~> 2.7)
   municipitaly2!
-  rake (~> 13.2.1)
+  rake (~> 13.3)
   rspec (~> 3.13)
-  rubocop (~> 1.64.1)
-  simplecov (~> 0.22.0)
+  rubocop (~> 1.80)
+  simplecov (~> 0.22)
 
 BUNDLED WITH
-   2.5.11
+   2.7.2

data/README.md

@@ -14,6 +14,12 @@ Thanks to natydev for the brilliant project.
 
 Add this line to your application's Gemfile:
 
+```ruby
+gem 'municipitaly2'
+```
+
+or if you want to use directly from the git repo:
+
 ```ruby
 gem 'municipitaly2', git: 'https://github.com/yupswing/municipitaly2.git', branch: 'master'
 ```
@@ -252,5 +258,6 @@ Check the `tools` folder.
 The tool is rought but it gets the job done. Hopefully I will improve it in the future.
 
 ### Generate vendor/data/municipalities.csv
+
 Update links in `tools/generate.rb` (and/or data in `tools/data/istat*`) and execute
 `./tools/generate.rb`

data/lib/municipitaly2/search.rb

@@ -15,11 +15,18 @@ module Municipitaly2
   class Search
     include DataCaller
 
-    CLASS_METHODS = %i[zone_from_code region_from_istat regions_from_zone_code
-                       province_from_name province_from_istat
-                       province_from_acronym provinces_from_region_istat
-                       provinces_from_zone_code municipalities_from_name
-                       municipality_from_cadastrial municipality_from_istat
+    CLASS_METHODS = %i[zone_from_code
+                       region_from_name
+                       region_from_istat
+                       regions_from_zone_code
+                       province_from_name
+                       province_from_istat
+                       province_from_acronym
+                       provinces_from_region_istat
+                       provinces_from_zone_code
+                       municipalities_from_name
+                       municipality_from_cadastrial
+                       municipality_from_istat
                        municipalities_from_postal_code
                        municipalities_from_province_istat
                        municipalities_from_region_istat
@@ -50,6 +57,20 @@ module Municipitaly2
       end
     end
 
+    # returns a +Municipitaly2::Region+ object from a <b>region name</b> term
+    #
+    # example usage:
+    #   region = Search.region_from_name('liguria')
+    def region_from_name # :doc:
+      term_set = Municipitaly2.sanitize_term(term)
+      return nil if term_set.size < 3
+
+      data.regions.find do |r|
+        name_set = Municipitaly2.sanitize_term(r.name)
+        name_set =~ Regexp.new(term_set)
+      end
+    end
+
     # returns a +Municipitaly2::Region+ object from a <b>region istat</b> term
     #
     # example usage:
@@ -103,8 +124,9 @@ module Municipitaly2
     # example usage:
     #   province = Search.province_from_acronym('MI')
     def province_from_acronym # :doc:
+      acronym = term.strip.upcase
       data.provinces.find do |p|
-        p.acronym == term
+        p.acronym == acronym
       end
     end
 
@@ -136,6 +158,9 @@ module Municipitaly2
     # Term can be a partial string and is case insensitive.
     # The optional parameter +greedy+ [boolean] permit to serch exact term
     # name (if false) or partial word (true by default).
+    # Matches are sorted by relevance: exact matches first, then starting with the
+    # term, then words starting with the term, then other matches. Within each
+    # group, matches are sorted by population (descending) and then by name.
     #
     # example usage:
     #   municipalities = Search.municipalities_from_name('monte')
@@ -146,14 +171,15 @@ module Municipitaly2
 
       return [] if term_set.size < 3
 
-      regexp = if greedy
-                 Regexp.new(term_set, true)
-               else
-                 Regexp.new("^#{term_set}$", true)
-               end
-      data.municipalities.select do |m|
-        Municipitaly2.sanitize_term(m.name) =~ regexp || (m.name_alt && Municipitaly2.sanitize_term(m.name_alt) =~ regexp)
-      end
+      # regex per match "greedy" e per match esatto
+      exact_re = Regexp.new("^#{term_set}$", true)
+      search_re = greedy ? Regexp.new(term_set, true) : exact_re
+
+      # search results
+      matches = filter(data.municipalities, search_re: search_re)
+
+      # sorts results by relevance
+      matches.sort_by { |match| rank(match, term: term_set, exact_re: exact_re, greedy: greedy) }
     end
 
     # returns a +Municipitaly2::Municipality+ object from a <b>cadastrial
@@ -229,5 +255,39 @@ module Municipitaly2
         istats.include? m.province_istat
       end
     end
+
+    # filters municipalities/provinces (name, name_alt required)
+    def filter(list, search_re:)
+      list.select do |item|
+        name_s = Municipitaly2.sanitize_term(item.name)
+        alt_s = item.name_alt && Municipitaly2.sanitize_term(item.name_alt)
+        (name_s =~ search_re) || (alt_s && alt_s =~ search_re)
+      end
+    end
+
+    # rank municipalities/provinces (name, name_alt, population required)
+    def rank(match, term:, exact_re:, greedy: true)
+      name_s = Municipitaly2.sanitize_term(match.name)
+      alt_s = match.name_alt && Municipitaly2.sanitize_term(match.name_alt)
+      names_s = [name_s, alt_s].compact
+
+      exact_match = names_s.any? { |n| n =~ exact_re }
+      any_word_starts = names_s.any? { |n| n.split.any? { |w| w.start_with?(term) } }
+
+      # Order: 0 = exact, 2 = any word starts, 3 = contains
+      priority = if !greedy || exact_match
+                   0 # Exact match
+                 # Disabled because it causes problems in some cases, like putting San Giuliano Milanese after Milazzo
+                 #  elsif names_s.any? { |s| s.start_with?(q) }
+                 #    1 # Starts with the term
+                 elsif any_word_starts
+                   2 # Any word starts with the term
+                 else
+                   3 # Other (match inside any word)
+                 end
+
+      # Priority, population (desc), name (asc)
+      [priority, -match.population.to_i, name_s]
+    end
   end
 end

data/lib/municipitaly2/version.rb

@@ -2,5 +2,5 @@
 
 module Municipitaly2
   # :nodoc:
-  VERSION = '2.0.2'
+  VERSION = '2.0.4'
 end

data/lib/municipitaly2.rb

@@ -24,6 +24,6 @@ module Municipitaly2
   # example usage:
   #   sanitized_term = Search.sanitize_term('Forlì Cesena')
   def self.sanitize_term(term) # :doc:
-    term.strip.downcase.tr('àâçèéêìòôù', 'aaceeeioou').gsub(/[^a-z]/, '')
+    term.strip.downcase.tr('àâçèéêìòôù', 'aaceeeioou').gsub(/[^a-z ]/, '')
   end
 end

data/municipitaly2.gemspec

@@ -32,11 +32,5 @@ Gem::Specification.new do |spec|
 
   spec.required_ruby_version = '>= 3.0.0'
 
-  spec.add_development_dependency 'bundler', '~> 2.5.11'
-  spec.add_development_dependency 'rake', '~> 13.2.1'
-  spec.add_development_dependency 'rspec', '~> 3.13'
-  spec.add_development_dependency 'rubocop', '~> 1.64.1'
-  spec.add_development_dependency 'simplecov', '~> 0.22.0'
-
-  spec.add_dependency 'csv', '~> 3.3.0' # removed from stdlib in Ruby 3.4
+  spec.add_dependency 'csv', '~> 3.3.5' # removed from stdlib in Ruby 3.4
 end