From 88d6de26a0e55430414b05e9d4d08a7a68102684 Mon Sep 17 00:00:00 2001
From: Nemael <100dragons@gmail.com>
Date: Tue, 6 Oct 2020 16:14:19 +0200
Subject: Improved the parser file and added some more comments, created a
 readme.txt file to explain LocationsParser.rb

---
 doc/import/LocationsParser.rb | 89 +++++++++++++++++++++++++++++++++++++++++++
 doc/import/readme.txt         | 10 +++++
 2 files changed, 99 insertions(+)
 create mode 100644 doc/import/LocationsParser.rb
 create mode 100644 doc/import/readme.txt

(limited to 'doc')

diff --git a/doc/import/LocationsParser.rb b/doc/import/LocationsParser.rb
new file mode 100644
index 0000000..3ce79c0
--- /dev/null
+++ b/doc/import/LocationsParser.rb
@@ -0,0 +1,89 @@
+#This file parses the data from the "Concertes" and "Dewey" folders
+#It creates a file "Locations.geojson" which is in the geoJson format to be used with a map
+
+require 'json'
+require 'csv'
+
+class Parser
+	def initialize()
+		@list_of_locations = {} #Contains all the locations from the Dewey and Concertes data
+		@list_of_locations["type"] = "FeatureCollection"
+		@list_of_locations["features"] = []
+	end
+	def parseDeweyFiles(data_file)
+		#Parses the .json files contained in the Dewey folder
+		data = JSON.parse(File.read(data_file))
+		i = 0
+		while i < data.size
+			new_item = {}
+			new_item["type"] = "Feature"
+			new_item["geometry"] = {}
+			new_item["geometry"]["type"] = "Point"
+			coords = data[i]["fields"]["position"].split(";")[1].gsub("POINT (","").gsub(")","").split(" ")
+			coords[0] = coords[0].to_f
+			coords[1] = coords[1].to_f
+			new_item["geometry"]["coordinates"] = coords
+			new_item["properties"] = {}
+			new_item["properties"]["name"] = data[i]["fields"]["name"]
+			new_item["properties"]["description"] = data[i]["fields"]["comment"]
+			new_item["properties"]["entry_number"] = data[i]["pk"]
+			new_item["properties"]["phone_number"] = data[i]["fields"]["phone"]
+			new_item["properties"]["website"] = data[i]["fields"]["web"]
+			new_item["properties"]["email"] = data[i]["fields"]["email"]
+			new_item["properties"]["address"] = data[i]["fields"]["address"]
+			new_item["properties"]["city"] = "" #No equivalent in Dewey data
+			new_item["properties"]["postal_code"] = "" #No equivalent in Dewey data
+			new_item["properties"]["categories"] = data[i]["fields"]["subcategories"]
+			new_item["properties"]["source"] = "Dewey"
+			new_item["properties"]["srid"] = data[i]["fields"]["position"].split(";")[0].gsub("SRID=","")
+			@list_of_locations["features"].push(new_item)
+			i += 1
+		end
+	end
+	def parseConcertesFiles(data_file, coordinates_file)
+		#Parses .csv files contained in the Concertes folder
+		data = CSV.parse(File.read(data_file), headers: true, :col_sep => ";")
+		coord = CSV.parse(File.read(coordinates_file), headers: true, :col_sep => ";")
+		i = 0
+		while i < data.size
+			new_item = {}
+			new_item["type"] = "Feature"
+			new_item["geometry"] = {}
+			new_item["geometry"]["type"] = "Point"
+			new_item["geometry"]["coordinates"] = [coord[i]["CoordLamb_X"].to_f, coord[i]["CoordLamb_Y"].to_f]
+			new_item["properties"] = {}
+			new_item["properties"]["name"] = data[i]["Denomination_FULL"]
+			new_item["properties"]["description"] = data[i]["description"]
+			new_item["properties"]["entry_number"] = data[i]["NumEntr"]
+			new_item["properties"]["phone_number"] = coord[i]["Tel"]
+			new_item["properties"]["website"] = coord[i]["Web"]
+			new_item["properties"]["email"] = coord[i]["Email"]
+			new_item["properties"]["address"] = coord[i]["Adresse"]
+			new_item["properties"]["city"] = data[i]["INS_COMMUNE"]
+			new_item["properties"]["postal_code"] = coord[i]["Code postal"]
+			new_item["properties"]["categories"] = [] #The categories from the Concertes data will not be used
+			new_item["properties"]["source"] = "Concertes"
+			new_item["properties"]["srid"] = "4326" #Not precised in Concertes data
+			@list_of_locations["features"].push(new_item)
+			i += 1
+		end
+	end
+	def writeToFile(write_file)
+		#Writes the list of locations in a pretty Json file
+		File.write(write_file, JSON.pretty_generate(@list_of_locations))
+	end
+end
+
+BEGIN {
+	puts "Starting parser"
+}
+
+parser = Parser.new()
+parser.parseConcertesFiles("Concertes/20200312_EntreprisesSignaletique.csv", "Concertes/20200312_EntreprisesCoordonnees.csv")
+parser.parseDeweyFiles("Dewey/dewey-maps-markers.json")
+parser.writeToFile("Locations.geojson")
+
+
+END {
+	puts "Ending parser, the data is available in the file 'Locations.geoJson'"
+}
diff --git a/doc/import/readme.txt b/doc/import/readme.txt
new file mode 100644
index 0000000..b534433
--- /dev/null
+++ b/doc/import/readme.txt
@@ -0,0 +1,10 @@
+The script LocationsParser.rb creates a file named "Locations.json", which contains all the points from the Concertes and Dewey database.
+It parses the .csv files from the Concertes folder and the .json files from the Dewey folder.
+To run it:
+	ruby parser.rb
+
+The main files it uses are:
+	Concertes/20200312_EntreprisesSignaletique.csv which contains the name of the points from the Concertes data
+	Concertes/20200312_EntreprisesCoordonnees.csv which contains the coordinates of the points from the Concertes data
+and
+	Dewey/dewey-maps-markers.json which contains the data of the points from the Dewey data
-- 
cgit v1.2.3