Merge pull request #569 from davemachado/update-md2json

Update md2json, validate_format, and validate_links

.travis.yml

@@ -1,10 +1,7 @@
-language: node_js
+language: python
+python: "3.6"
 notifications:
   email: true
-before_install:
-  - rvm install 2.4.0
-install:
-  - gem install httparty ruby-progressbar
 before_script:
   - cd build
 script:

build/build.sh

@@ -3,7 +3,6 @@
 # create json directory if not already present
 mkdir -p ../json
 # parse API README and print (minified) JSON to stdout, redirect to /json
-node condenseMd.js ../README.md > single_table.md
-node md2json.js single_table.md > ../json/entries.min.json
+./md2json.py ../README.md > ../json/entries.min.json
 # beautify the previously created JSON file, redirect to /json
 python -m json.tool ../json/entries.min.json > ../json/entries.json

build/condenseMd.js

@@ -1,63 +0,0 @@
-fs = require('fs')
-
-function setupMd(filename, anchor) {
-    fs.readFile(filename, 'utf8', function (err,text) {
-      if (err) {
-        return console.log(err);
-      }
-    var lines = text.split("\n"),
-        cur_line = 0,
-        line = "",
-        table_name = "",
-        col_num = 0,
-        cols = [],
-        rows = [],
-        arr = [];
-
-
-    function read_line() {
-        return lines[cur_line++];
-    }
-
-    while (true) {
-        var cols = [];
-        var rows = [];
-        while (line.indexOf(anchor) == -1 && cur_line != lines.length) {
-            line = read_line();
-        }
-        if (cur_line == lines.length) {
-            break;
-        }
-        table_name = line.split(anchor)[1];
-        read_line()
-        read_line()
-        while (true) {
-        	line = read_line()
-        	if (line.length < 2 || cur_line == lines.length) {
-        		break
-        	}
-			if (line.indexOf("|") == 0) {
-				arr.push(line + table_name)
-			} 
-        }
-
-    }
-    console.log(anchor + " entries")
-    console.log("API | Description | Auth | HTTPS | Link | Category")
-    console.log("|---|---|---|---|---|---|")
-    for (i = 0; i < arr.length; i++) {
-    	console.log(arr[i])
-    }
-  });
-}
-
-if (process.argv.length < 3) {
-    console.log("No .md file passed!");
-    return;
-}
-if (process.argv.length < 4) {
-  anchorText = "###";
-} else {
-  anchorText = process.argv[3];
-}
-setupMd(process.argv[2].toString(), anchorText);

build/main.sh

@@ -30,7 +30,7 @@ else
 fi
 
 echo "running format validation..."
-./validate_format.rb $FORMAT_FILE
+./validate_format.py $FORMAT_FILE
 if [[ $? != 0 ]]; then
   echo "format validation failed!"
   exit 1

build/md2json.js

@@ -1,134 +0,0 @@
-fs = require('fs')
-
-function md_trim(str, context) {
-    str = str.replace(/(^\s+)|(\s+$)/g, "");
-
-    if (context == 1) { // Name
-        // placeholder for any formatting on name value
-    } else if (context == 2) { // Description
-        str = str.replace(".", ""); // remove ending periods on descriptions
-    } else if (context == 3) { // Auth
-        if (str.toUpperCase() == "NO") {
-            str = null
-        } else {
-            str = str.replace("`", "").replace("`", "")
-        }
-    } else if (context == 4) { // HTTPS
-        if (str.toUpperCase() == "YES") {
-            str = true
-        } else {
-            str = false
-        }
-    } else if (context == 5) { // Link
-        str = str.replace("[Go!]", "").slice(1, -1);
-    }
-    return str;
-}
-
-function handle(filename, anchor) {
-    fs.readFile(filename, 'utf8', function (err,text) {
-      if (err) {
-        return console.log(err);
-      }
-    var lines = text.split("\n");
-    var cur_line = 0;
-    var line = ""
-    var table_name = "";
-    var col_num = 0;
-    var cols = [];
-    var rows = [];
-    var entry_count = 0;
-
-    function read_line() {
-        return lines[cur_line++];
-    }
-    var root = {};
-    while (true) {
-        var cols = [];
-        var rows = [];
-        while (line.indexOf(anchor) == -1 && cur_line != lines.length) {
-            line = read_line();
-        }
-        if (cur_line == lines.length) {
-            break;
-        }
-        table_name = line.split(anchor)[1];
-        table_name = md_trim(table_name, 0)
-
-        line = read_line()
-
-        if (line) {
-            line = line.split("|")
-            for (var j in line) {
-
-                line[j] = md_trim(line[j], 0)
-                if ((j == 0 || j == line.length - 1) && line[j] === "") {
-
-                } else {
-                    cols.push(line[j]);
-                }
-            }
-            if (line.length) {
-                cols = line;
-                rows.push(cols)
-            } else {
-                console.error("markdown expect column title")
-                break;
-            }
-        } else {
-            console.error("markdown expect table content")
-            break;
-        }
-
-        line = read_line()
-
-        if (!line) {
-            console.error("markdown expect table spliter")
-            break;
-        }
-        line = read_line()
-        while (line.indexOf("|") != -1 && cur_line != lines.length) {
-
-            var line_this = line.split("|")
-            var row = []
-            for (var j in line_this) {
-                line_this[j] = md_trim(line_this[j], j)
-                if ((j == 0 || j == line_this.length - 1) && line_this[j] === "") {
-
-                } else {
-                    row.push(line_this[j]);
-                }
-
-            }
-            rows.push(row);
-            entry_count++;
-            line = read_line()
-        }
-
-        var data=[];
-        for (var j in rows) {
-            if (j != 0) {
-                var ele = {};
-                for (var k in rows[j]) {
-                    ele[rows[0][k]] = rows[j][k];
-                }
-                data.push(ele);
-            }
-        }
-        root["count"] = entry_count;
-        root[table_name] = data;
-    }
-    console.log(JSON.stringify(root));
-  });
-}
-
-if (process.argv.length < 3) {
-    console.log("No .md file passed!");
-    return;
-}
-if (process.argv.length < 4) {
-  anchorText = "###";
-} else {
-  anchorText = process.argv[3];
-}
-handle(process.argv[2].toString(), anchorText);

build/md2json.py

@@ -0,0 +1,48 @@
+#!/usr/bin/env python3
+
+import json
+import sys
+
+
+def markdown_to_json(filename, anchor):
+    """Convert a Markdown file into a JSON string"""
+    category = ""
+    entries = []
+    with open(filename) as fp:
+        lines = (line.rstrip() for line in fp)
+        lines = list(line for line in lines if line \
+                    and line.startswith(anchor) or line.startswith('| '))
+    for line in lines:
+        if line.startswith(anchor):
+            category = line.split(anchor)[1].strip()
+            continue
+        chunks = [x.strip() for x in line.split('|')[1:-1]]
+        entry = {
+            'API': chunks[0],
+            'Description': chunks[1],
+            'Auth': None if chunks[2].upper() == 'NO' else chunks[2].strip('`'),
+            'HTTPS': True if chunks[3].upper() == 'YES' else False,
+            'Link': chunks[4].replace('[Go!]', '')[1:-1],
+            'Category': category,
+        }
+        entries.append(entry)
+    final = {
+        'count': len(entries),
+        'entries': entries,
+    }
+    return json.dumps(final)
+
+
+def main():
+    num_args = len(sys.argv)
+    if num_args < 2:
+        print("No .md file passed")
+        sys.exit(1)
+    if num_args < 3:
+        anchor = '###'
+    else:
+        anchor = sys.argv[2]
+    print(markdown_to_json(sys.argv[1], anchor))
+
+if __name__ == "__main__":
+    main()

build/validate_format.py

@@ -0,0 +1,111 @@
+#!/usr/bin/env python3
+
+import json
+import string
+import sys
+
+anchor = '###'
+auth_keys = ['apiKey', 'OAuth', 'X-Mashape-Key', 'No']
+punctuation = ['.', '?', '!']
+https_keys = ['Yes', 'No']
+
+index_title = 0
+index_desc = 1
+index_auth = 2
+index_https = 3
+index_link = 4
+
+errors = []
+
+
+def add_error(line_num, message):
+    """adds an error to the dynamic error list"""
+    err = '(L{:03d}) {}'.format(line_num+1, message)
+    errors.append(err)
+
+
+def check_format(filename):
+    """
+    validates that each line is formatted correctly,
+    appending to error list as needed
+    """
+    with open(filename) as fp:
+        lines = list(line.rstrip() for line in fp)
+
+    # START Alphabetical Order
+    category = ""
+    sections = {}
+    section_line_num = {}
+    for line_num, line in enumerate(lines):
+        if line.startswith(anchor):
+            category = line.split(anchor)[1].strip()
+            sections[category] = []
+            section_line_num[category] = line_num
+            continue
+        if not line.startswith('|') or line.startswith('|---'):
+            continue
+        title = [x.strip() for x in line.split('|')[1:-1]][0].upper()
+        sections[category].append(title)
+
+    for category, entries in sections.items():
+        if sorted(entries) != entries:
+            add_error(section_line_num[category], '{} section is not in alphabetical order'.format(category))
+    # END Alphabetical Order
+
+    # START Check Entries
+    for line_num, line in enumerate(lines):
+        if not line.startswith('|') or line.startswith('|---'):
+            continue
+        segments = line.split('|')[1:-1]
+        # START Global
+        for segment in segments:
+            # every line segment should start and end with exactly 1 space
+            if len(segment) - len(segment.lstrip()) != 1 or len(segment) - len(segment.rstrip()) != 1:
+                add_error(line_num, "each segment must start and end with exactly 1 space")
+        # END Global
+        segments = [seg.strip() for seg in segments]
+        # START Description
+        # first character should be capitalized
+        char = segments[index_desc][0]
+        if char.upper() != char:
+            add_error(line_num, "first char of Description is not capitalized")
+        # last character should not punctuation
+        char = segments[index_desc][-1]
+        if char in punctuation:
+            add_error(line_num, "description should not end with {}".format(char))
+        # END Description
+        # START Auth
+        # values should conform to valid options only
+        auth = segments[index_auth].replace('`', '')
+        if auth not in auth_keys:
+            add_error(line_num, "{} is not a valid Auth option".format(auth))
+        # END Auth
+        # START HTTPS
+        # values should conform to valid options only
+        https = segments[index_https]
+        if https not in https_keys:
+            add_error(line_num, "{} is not a valid HTTPS option".format(https))
+        # END HTTPS
+        # START Link
+        # url should be wrapped in '[Go!]()' Markdown syntax
+        link = segments[index_link]
+        if not link.startswith('[Go!](http') or not link.endswith(')'):
+            add_error(line_num, 'link format should be "[Go!](LINK)"')
+        # END Link
+    # END Check Entries
+
+def main():
+    num_args = len(sys.argv)
+    if num_args < 2:
+        print("No .md file passed")
+        sys.exit(1)
+
+    check_format(sys.argv[1])
+    if len(errors) > 0:
+        for err in errors:
+            print(err)
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

build/validate_format.rb

@@ -1,111 +0,0 @@
-#!/usr/bin/env ruby
-
-auth_keys = ['apiKey', 'OAuth', 'X-Mashape-Key', 'No']
-punctuation = ['.', '?', '!']
-https_keys = ['Yes', 'No']
-
-INDEX_TITLE = 1
-INDEX_DESCRIPTION = 2
-INDEX_AUTH = 3
-INDEX_HTTPS = 4
-INDEX_LINK = 5
-filename = ARGV[0]
-$errors = []
-
-def add_error(line_num, val_index, message)
-    case val_index
-    when INDEX_TITLE
-        segment = "Title"
-    when INDEX_DESCRIPTION
-        segment = "Description"
-    when INDEX_AUTH
-        segment = "Auth"
-    when INDEX_HTTPS
-        segment = "HTTPS"
-    when INDEX_LINK
-        segment = "Link"
-    end
-    $errors.push("(L%03d) %-14.14s #{message}" % [line_num, segment])
-end
-
-################### CHECK ALPHABETICAL ORDER ###################
-section = ''
-sections = []
-section_to_line_num = {}
-section_to_entries = Hash.new {|h,k| h[k] = Array.new }
-File.foreach(filename).with_index do | line, line_num |
-	if line.start_with?('###')
-		section = line.sub('###', '').lstrip.chop
-		sections.push(section)
-		section_to_line_num[section] = line_num + 1
-	end
-	# Skip non-markdown table lines and table schema lines
-    if !line.start_with?('|') || line.eql?("|---|---|---|---|---|\n")
-        next
-    end
-    # char to check is the first column
-    check_char = line.split("|")[1].strip.upcase
-    section_to_entries[section].push(check_char)
-end
-sections.each do | sect |
-	if section_to_entries[sect] != section_to_entries[sect].sort
-		add_error(section_to_line_num[sect], INDEX_TITLE, "#{sect} section is not in alphabetical order")
-	end
-end
-
-#################### CHECK LINE ENTRIES ########################
-File.foreach(filename).with_index do | line, line_num |
-    line_num += 1
-        
-    # Skip non-markdown table lines and table schema lines
-    if !line.start_with?('|') || line.eql?("|---|---|---|---|---|\n")
-        next
-    end
-
-    values = line.split("|")
-
-    ################### GLOBAL ###################
-    values.each.with_index do |val, val_index|
-        msg = ""
-        case val_index
-        when INDEX_TITLE..INDEX_LINK
-            # every line segment should start and end with exactly 1 space
-            if val[/\A */].size != 1 || val[/ *\z/].size != 1
-                add_error(line_num, val_index, "string should start and end with exactly 1 space")
-            end
-        end
-    end
-    ################# DESCRIPTION ################
-    # First character should be capitalized
-    desc_val = values[INDEX_DESCRIPTION].lstrip.chop
-    if !/[[:upper:]]/.match(desc_val[0])
-        add_error(line_num, INDEX_DESCRIPTION, "first char not uppercase")
-    end
-    # value should not be punctuated
-    last_char = desc_val[desc_val.length-1]
-    if punctuation.include?(last_char)
-        add_error(line_num, INDEX_DESCRIPTION, "description should not end with \"#{last_char}\"")
-    end
-    #################### AUTH ####################
-    # Values should conform to valid options only
-    auth_val = values[INDEX_AUTH].lstrip.chop.tr('``', '')
-    if !auth_keys.include?(auth_val)
-        add_error(line_num, INDEX_AUTH, "not a valid option: #{auth_val}")
-    end
-    #################### HTTPS ###################
-    # Values should be either "Yes" or "No"
-    https_val = values[INDEX_HTTPS].lstrip.chop
-    if !https_keys.include?(https_val)
-        add_error(line_num, INDEX_HTTPS, "must use \"Yes\" or \"No\": #{https_val}")
-    end
-    #################### LINK ####################
-    # Url should be wrapped in "[Go!]" view
-    link_val = values[INDEX_LINK].lstrip.chop
-    if !link_val.start_with?("[Go!](") || !link_val.end_with?(')')
-        add_error(line_num, INDEX_LINK, "format should be \"[Go!](<LINK>)\": #{link_val}")
-    end
-end
-$errors.each do | e |
-    puts e
-end
-exit($errors.length)

build/validate_links.py

@@ -0,0 +1,53 @@
+#!/usr/bin/env python3
+
+import httplib2
+import json
+import socket
+import sys
+
+
+def parse_links(filename):
+    """Returns a list of links from JSON object"""
+    data = json.load(open(filename))
+    links = []
+    for entry in data['entries']:
+        link = entry['Link']
+        https = True if link.startswith('https') else False
+        x = {
+            'link': link,
+            'https': https,
+        }
+        links.append(x)
+    return links
+
+
+def validate_links(links):
+    """Checks each entry in JSON file for live link"""
+    print('Validating {} links...'.format(len(links)))
+    errors = []
+    for each in links:
+        link = each['link']
+        h = httplib2.Http(disable_ssl_certificate_validation=True, timeout=5)
+        try:
+            resp = h.request(link, 'HEAD')
+            code = int(resp[0]['status'])
+            # check if status code is a client or server error
+            if code >= 404:
+                errors.append('{}: {}'.format(code, link))
+        except TimeoutError:
+            errors.append("TMO: " + link)
+        except socket.error as socketerror:
+            errors.append("SOC: {} : {}".format(socketerror, link))
+    return errors
+
+if __name__ == "__main__":
+    num_args = len(sys.argv)
+    if num_args < 2:
+        print("No .json file passed")
+        sys.exit(1)
+    errors = validate_links(parse_links(sys.argv[1]))
+    if len(errors) > 0:
+        for err in errors:
+            print(err)
+        sys.exit(1)
+

build/validate_links.rb

@@ -1,81 +0,0 @@
-#!/usr/bin/env ruby
-require 'httparty'
-require 'ruby-progressbar'
-require 'uri'
-allowed_codes = [200, 302, 403, 429]
-allowed_links = ["https://www.yelp.com/developers/documentation/v3"]
-args = ARGV
-filename = args[0]
-contents = File.open(filename, 'rb') { |f| f.read }
-raw_links = URI.extract(contents, ['http', 'https'])
-# Remove trailing ')' from entry URLs
-links = []
-raw_links.each do |link|
-    if link.end_with?(')')
-        links.push(link[0...-1])
-    else
-        links.push(link)
-    end
-end
-if links.length <= 0
-    puts "no links to check"
-    exit(0)
-end
-fails = []
-# Fail on any duplicate elements
-dup = links.select{|element| links.count(element) > 1}
-if dup.uniq.length > 0
-    dup.uniq.each do |e|
-        fails.push("(DUP): #{e}")
-    end
-end
-# Remove any duplicates from array
-links = links.uniq
-count = 0
-total = links.length
-progressbar = ProgressBar.create(:total => total,
-    :format => "%a %P% | Processed: %c from %C")
-# GET each link and check for valid response code from allowed_codes
-links.each do |link|
-    begin
-        count += 1
-        if allowed_links.include?(link)
-            next
-        end
-        res = HTTParty.get(link, timeout: 10)
-        if res.code.nil?
-            fails.push("(NIL): #{link}")
-            next
-        end
-        if !allowed_codes.include?(res.code)
-            fails.push("(#{res.code}): #{link}")
-        end
-    rescue HTTParty::RedirectionTooDeep
-        fails.push("(RTD): #{link}")
-    rescue Net::ReadTimeout
-        fails.push("(TMO): #{link}")
-    rescue Net::OpenTimeout
-        fails.push("(TMO): #{link}")
-    rescue OpenSSL::SSL::SSLError
-        fails.push("(SSL): #{link}")
-    rescue SocketError
-        fails.push("(SOK): #{link}")
-    rescue Errno::ECONNREFUSED
-        fails.push("(CON): #{link}")
-    rescue Errno::ECONNRESET
-        next
-    end
-    progressbar.increment
-end
-puts "#{count}/#{total} links checked"
-if fails.length <= 0
-    puts "all links valid"
-    exit(0)
-else
-    puts "-- RESULTS --"
-    fails.sort!
-    fails.each do |e|
-        puts e
-    end
-    exit(1)
-end

json/entries.json

@@ -197,7 +197,7 @@
             "API": "BookNomads",
             "Auth": null,
             "Category": "Books",
-            "Description": "Books published in the Netherlands and Flanders (about 25 million), book covers, and related data",
+            "Description": "Books published in the Netherlands and Flanders (about 2.5 million), book covers, and related data",
             "HTTPS": true,
             "Link": "https://www.booknomads.com/dev"
         },
@@ -765,7 +765,7 @@
             "API": "JSONbin.io",
             "Auth": "apiKey",
             "Category": "Development",
-            "Description": "Free JSON storage service Ideal for small scale Web apps, Websites and Mobile apps",
+            "Description": "Free JSON storage service. Ideal for small scale Web apps, Websites and Mobile apps",
             "HTTPS": true,
             "Link": "https://jsonbin.io"
         },
@@ -1741,7 +1741,7 @@
             "API": "BusinessUSA",
             "Auth": "apiKey",
             "Category": "Government",
-            "Description": "BusinessUSA gives developers access to authoritative information on US. programs, events, services and more",
+            "Description": "BusinessUSA gives developers access to authoritative information on U.S. programs, events, services and more",
             "HTTPS": true,
             "Link": "https://business.usa.gov/developer"
         },
@@ -1781,7 +1781,7 @@
             "API": "Regulations.gov",
             "Auth": "apiKey",
             "Category": "Government",
-            "Description": "Regulationsgov provides access to Federal regulatory materials and increases public participation and their understanding of the Federal rule making process",
+            "Description": "Regulations.gov provides access to Federal regulatory materials and increases public participation and their understanding of the Federal rule making process",
             "HTTPS": true,
             "Link": "https://regulationsgov.github.io/developers/"
         },
@@ -1837,7 +1837,7 @@
             "API": "Medicare",
             "Auth": null,
             "Category": "Health",
-            "Description": "Access to the data from the CMS - medicaregov",
+            "Description": "Access to the data from the CMS - medicare.gov",
             "HTTPS": true,
             "Link": "https://data.medicare.gov/developers"
         },
@@ -2477,7 +2477,7 @@
             "API": "UPC database",
             "Auth": "apiKey",
             "Category": "Open Data",
-            "Description": "More than 15 million barcode numbers from all around the world",
+            "Description": "More than 1.5 million barcode numbers from all around the world",
             "HTTPS": true,
             "Link": "https://upcdatabase.org/api"
         },
@@ -2517,7 +2517,7 @@
             "API": "Drupal.org",
             "Auth": null,
             "Category": "Open Source Projects",
-            "Description": "Drupalorg",
+            "Description": "Drupal.org",
             "HTTPS": true,
             "Link": "https://www.drupal.org/drupalorg/docs/api"
         },
@@ -2733,7 +2733,7 @@
             "API": "inspirehep.net",
             "Auth": null,
             "Category": "Science",
-            "Description": "High Energy Physics info system",
+            "Description": "High Energy Physics info. system",
             "HTTPS": true,
             "Link": "https://inspirehep.net/info/hep/api?ln=en"
         },
@@ -2749,7 +2749,7 @@
             "API": "Minor Planet Center",
             "Auth": null,
             "Category": "Science",
-            "Description": "Asterankcom Information",
+            "Description": "Asterank.com Information",
             "HTTPS": false,
             "Link": "http://www.asterank.com/mpc"
         },
@@ -2949,7 +2949,7 @@
             "API": "Meetup.com",
             "Auth": "apiKey",
             "Category": "Social",
-            "Description": "Data about Meetups from Meetupcom",
+            "Description": "Data about Meetups from Meetup.com",
             "HTTPS": true,
             "Link": "https://www.meetup.com/meetup_api/"
         },