gallicagram 1.0.1 → 1.0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: dc880e4aa64ab9c8cb35d2dbb9f2fadb7d5280195470ccbb2b9cb76bfffb4501
-  data.tar.gz: 9c5cf57821a16e16ce13b33c6ebeb1fde5386a16d78f28250bf03be346d981bf
+  metadata.gz: 550bf9ebdcf99a41e01e157ba09dc5e864ef4fc531036b4afdd0501a4d5c4ad3
+  data.tar.gz: 6a18e0c6719baef37699c5035c7abc53008cca58040368fdbcf56ccb687de9f1
 SHA512:
-  metadata.gz: 3bf34772e3c3828fb08da67e83d8c71f2042ae9eb7edfd5d18af0311e991c172c4561242c72eaef878528af896c2fbbbc5849578d6143c277d5800ede99fded6
-  data.tar.gz: 62d37214f2d572629b45352e93d675a9276ed9c98e95117dd30e7462dd0a70d8dfe3d448e42dbb94fb987bee32afd71ab5aa6b96b35de2b6407f8c9eab1eb565
+  metadata.gz: bbdb13303e02606ac3eea5911787815e5f52a0081adc59f5a7c96cfcfa962ca4edfb49dc2a93c020f973771bd18facd8b10812cb9dddad7b24f0404d9ae82c74
+  data.tar.gz: 428ddb548775277156091035b04f9d72f3b4549ea39a9842bbc7294a2a93e081e6ce65db402dba921dd119235e4b3a3d9f8e3e9aeab415907a9876d243a91af2

data/lib/gallicagram.rb

@@ -2,44 +2,72 @@ class Gallicagram
 
 	require 'open-uri'
 	require 'cgi'
+	require 'csv'
   
 	# query = string or array of strings
 	# corpus = ["lemonde","livres","presse"]
 	# resolution = ["year", "month"]
-	def self.search(query,corpus="lemonde",start_date="1900",end_date="2000",resolution="month",sum=false) 
+	def self.search(query,corpus="lemonde",start_date="1900",end_date="2000",resolution="month",sum=false)
 
-		query = format_query(query, sum)
+		query = [query] unless query.kind_of?(Array)
+		output = ""
+		query.each_with_index do |word, index|
+			query = format_query(word, sum)
+			response = call_api(word, corpus, start_date, end_date)
+			unless index == 0
+				response = response.gsub("n,gram,annee,mois,jour,total", "\n").strip
+			end
+			output << response
+		end
 
-		# We search through the Gallicagram API
-		url = "https://shiny.ens-paris-saclay.fr/guni/corpus=#{corpus}_#{query}_from=#{start_date}_to=#{end_date}"
+		if corpus == "livres" && resolution == "month"
+			resolution = "year"
+		end
 
-		response = URI.open(url)
+		data = group_by_resolution(output, resolution)
 
-		return response.read # to read the output: CSV.parse(response.read)
-  end
+		return data
+	end
 end
 
 private
 
 def format_query(query, sum)
-	if query.kind_of?(Array)
-		query_string = ""
-		query.each_with_index do |word, i|
-			word = CGI.escape(word.strip.gsub(" ", "%20"))
-			if i == 0
-				query_string = query_string + word
-			else
-				if sum == true 
-					query_string = query_string + "+" + word
-				else
-					query_string = query_string + "&" + word
-				end
-			end
-		end
-	else
-		query_string = CGI.escape(query.strip.gsub(" ", "%20"))
-	end
+	
+	query_string = CGI.escape(query.strip.gsub(" ", "%20"))
 
 	return query_string
 
+end
+
+def call_api(query, corpus, start_date, end_date)
+	# We search through the Gallicagram API
+	url = "https://shiny.ens-paris-saclay.fr/guni/query?corpus=#{corpus}&mot=#{CGI.escape(query)}&from=#{start_date}&to=#{end_date}"
+
+	response = URI.open(url)
+
+	return response.read
+end
+
+def group_by_resolution(data, resolution)
+	csv_parsing = CSV.parse(data, :headers => true)
+	clean_data_array = []
+	case resolution 
+	when "year"
+		csv_parsing.group_by { |word| [word["annee"], word["gram"]] }.each do |cp|
+			sum = cp[1].sum { |word| word["total"].to_i }
+			new_row = cp[0]
+			new_row << sum
+			clean_data_array << new_row
+		end
+	when "month"
+		csv_parsing.group_by { |word| [word["annee"], word["mois"], word["gram"]] }.each do |cp|
+			sum = cp[1].sum { |word| word["total"].to_i }
+			new_row = cp[0]
+			new_row << sum
+			clean_data_array << new_row
+		end
+	end
+
+	return clean_data_array
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: gallicagram
 version: !ruby/object:Gem::Version
-  version: 1.0.1
+  version: 1.0.6
 platform: ruby
 authors:
 - Nicolas Le Roux
@@ -64,7 +64,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.7
+rubygems_version: 3.4.12
 signing_key:
 specification_version: 3
 summary: A ruby gem to manage Gallicagram data