ZMediumToMarkdown 2.0.5 → 2.0.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4d39b14b2d274522cbd880b0673012c40b749e693d706d8f6906e8df4f19d640
-  data.tar.gz: 5225ba58b765a96a4894f28cae5cb1394aca8d92dbce5bb7e8bfa74bbe48aa30
+  metadata.gz: 15f4bb468ab40811678a1a7b38dc51aa6e442b28a8da0b3835dce158f6d90fd4
+  data.tar.gz: 67715feec8e9e7c9f798a61e61529e7846b2db42c86d0c8bd9dd43f3d2de971d
 SHA512:
-  metadata.gz: 2ab477a2f0bb769e53eccc479e3839a7963c98ef97a0d46e51d3bf26f04e8cbd555c4f515d5518dba455754a6e29d20044cc87e60e1ae1a9256d286ebdf455db
-  data.tar.gz: a7ed47c1335ffca2ff33a5a21046c06c5689b6cd4225a4d26854b0ee334eb77aa3c04e5bda8c77d829ad64b55857ccaa14897681859c96a4e6b0dcce1af1b12c
+  metadata.gz: 84f8eece59e468fb75768af6ed756dd96812ea81d8c6e6ecaeabf2c090db5f5bea10c39e8fc8693720322681f5ec902966371d4a95476f6f30ac8ada0782702e
+  data.tar.gz: 66c66d9b514fd8b0c81776e3dff2a466e91d291ebd9c466de8f6ca8ad19e7ba1d89aa154fa768e746194031805bf8722dbb8f0569b143e2700d04b550c0ce35f

data/bin/ZMediumToMarkdown

@@ -76,7 +76,7 @@ end
 begin 
     puts "#https://github.com/ZhgChgLi/ZMediumToMarkdown"
     puts "You have read and agree with the Disclaimer."
-    Main.new()
+    #Main.new()
     puts "Execute Successfully!!!"
     puts "#https://github.com/ZhgChgLi/ZMediumToMarkdown"
     puts "#Thanks for using this tool."
@@ -86,4 +86,9 @@ rescue => e
     puts e.backtrace
     puts "#Please feel free to open an Issue or submit a fix/contribution via Pull Request on:\n"
     puts "#https://github.com/ZhgChgLi/ZMediumToMarkdown\n"
-end
+end
+
+obj = JSON.parse('{ "id": "e41429008434_63", "name": "35a0", "type": "ULI", "href": null, "layout": null, "metadata": null, "text": "[New] Customer reviews", "hasDropCap": null, "dropCapImage": null, "markups": [ { "type": "A", "start": 6, "end": 22, "href": "https://developer.apple.com/documentation/appstoreconnectapi/app_store/customer_reviews", "anchorType": "LINK", "userId": null, "linkMetadata": null, "__typename": "Markup" }, { "type": "STRONG", "start": 0, "end": 6, "href": null, "anchorType": null, "userId": null, "linkMetadata": null, "__typename": "Markup" } ], "__typename": "Paragraph", "iframe": null, "mixtapeMetadata": null }')
+p = Paragraph.new(obj, "100")
+r = MarkupParser.new(p, false)
+puts r.parse()

data/lib/Helper.rb

@@ -19,6 +19,10 @@ class Helper
         content
     end
 
+    def self.escapeMarkdown(text)
+        text.gsub(/(\*|_|`|\||\\|\{|\}|\[|\]|\(|\)|#|\+|\-|\.|\!)/){ |x| "\\#{x}" }
+    end
+
     def self.escapeHTML(text)
         if text == "<"
             "&lt;"
@@ -101,8 +105,8 @@ class Helper
         result = "---\n"
         result += "title: #{title}\n"
         result += "author: #{postInfo.creator}\n"
-        result += "date: #{postInfo.firstPublishedAt.strftime('%Y-%m-%dT%H:%M:%S.%LZ')}\n"
-        result += "last_modified_at: #{postInfo.latestPublishedAt.strftime('%Y-%m-%dT%H:%M:%S.%LZ')}\n"
+        result += "date: #{postInfo.firstPublishedAt.strftime('%Y-%m-%dT%H:%M:%S.%L%z')}\n"
+        result += "last_modified_at: #{postInfo.latestPublishedAt.strftime('%Y-%m-%dT%H:%M:%S.%L%z')}\n"
         result += "categories: #{postInfo.collectionName}\n"
         result += "tags: [#{postInfo.tags.join(",")}]\n"
         result += "description: #{postInfo.description}\n"
@@ -185,9 +189,14 @@ class Helper
     end
 
         
-    def self.createWatermark(postURL)
+    def self.createWatermark(postURL, isForJekyll)
+        jekyllOpen = ""
+        if isForJekyll
+            jekyllOpen = "{:target=\"_blank\"}"
+        end
+
         text = "\r\n\r\n\r\n"
-        text += "_Converted [Medium Post](#{postURL}) by [ZMediumToMarkdown](https://github.com/ZhgChgLi/ZMediumToMarkdown)._"
+        text += "_Converted [Medium Post](#{postURL})#{jekyllOpen} by [ZMediumToMarkdown](https://github.com/ZhgChgLi/ZMediumToMarkdown)#{jekyllOpen}._"
         text += "\r\n"
 
         text

data/lib/Models/Paragraph.rb

@@ -96,14 +96,23 @@ class Paragraph
             end
         end
 
-        i = 0
-        while i = orgText.index(/(\*|_|`|\||\\|\{|\}|\[|\]|\(|\)|#|\+|\-|\.|\!)/, i + 1)
-            escapeMarkup = {
-                "type" => 'ESCAPE',
-                "start" => i,
-                "end" => i + 1
-            }
-            markups.append(Markup.new(escapeMarkup))
+        index = 0
+        orgText.each_char do |char|
+            
+            if char.chars.join()  =~ /(\*|_|`|\||\\|\{|\}|\[|\]|\(|\)|#|\+|\-|\.|\!)/
+                escapeMarkup = {
+                    "type" => 'ESCAPE',
+                    "start" => index,
+                    "end" => index + 1
+                }
+                markups.append(Markup.new(escapeMarkup))
+            end
+            
+            index += 1
+            if char.bytes.length >= 4
+                # some emoji need more space (in Medium)
+                index += 1
+            end
         end
 
         @markups = markups

data/lib/Parsers/BQParser.rb

@@ -16,7 +16,7 @@ class BQParser < Parser
 
     def parse(paragraph)
         if BQParser.isBQ(paragraph)
-            result = "> #{paragraph.text}"
+            result = "> #{paragraph.text} \n\n"
             result
         else
             if !nextParser.nil?

data/lib/Parsers/IframeParser.rb

@@ -19,6 +19,12 @@ class IframeParser < Parser
     end
 
     def parse(paragraph)
+
+        jekyllOpen = ""
+        if isForJekyll
+            jekyllOpen = "{:target=\"_blank\"}"
+        end
+
         if paragraph.type == 'IFRAME'
             
             if !paragraph.iframe.src.nil? && paragraph.iframe.src != ""
@@ -27,7 +33,7 @@ class IframeParser < Parser
                 url = "https://medium.com/media/#{paragraph.iframe.id}"
             end
 
-            result = "[#{paragraph.iframe.title}](#{url})"
+            result = "[#{paragraph.iframe.title}](#{url})#{jekyllOpen}"
 
             if !url[/(www\.youtube\.com)/].nil?
                 # is youtube
@@ -49,12 +55,12 @@ class IframeParser < Parser
                     if  ImageDownloader.download(absolutePath, imageURL)
                         relativePath = imagePathPolicy.getRelativePath(fileName)
                         if isForJekyll
-                            result = "\r\n\r\n[![#{title}](/#{relativePath} \"#{title}\")](#{params["url"]})\r\n\r\n"
+                            result = "\r\n\r\n[![#{title}](/#{relativePath} \"#{title}\")](#{params["url"]})#{jekyllOpen}\r\n\r\n"
                         else
-                            result = "\r\n\r\n[![#{title}](#{relativePath} \"#{title}\")](#{params["url"]})\r\n\r\n"
+                            result = "\r\n\r\n[![#{title}](#{relativePath} \"#{title}\")](#{params["url"]})#{jekyllOpen}\r\n\r\n"
                         end
                     else
-                        result = "\r\n[#{title}](#{params["url"]})\r\n"
+                        result = "\r\n[#{title}](#{params["url"]})#{jekyllOpen}\r\n"
                     end
                 end
             else
@@ -118,9 +124,9 @@ class IframeParser < Parser
                             createdAt = Time.parse(twitterObj["created_at"]).strftime('%Y-%m-%d %H:%M:%S')
                             result = "\n\n"
                             result += "■■■■■■■■■■■■■■ \n"
-                            result += "> **[#{twitterObj["user"]["name"]}](https://twitter.com/#{twitterObj["user"]["screen_name"]}) @ Twitter Says:** \n\n"
+                            result += "> **[#{twitterObj["user"]["name"]}](https://twitter.com/#{twitterObj["user"]["screen_name"]})#{jekyllOpen} @ Twitter Says:** \n\n"
                             result += "> > #{fullText} \n\n"
-                            result += "> **Tweeted at [#{createdAt}](#{ogURL}).** \n\n"
+                            result += "> **Tweeted at [#{createdAt}](#{ogURL})#{jekyllOpen}.** \n\n"
                             result += "■■■■■■■■■■■■■■ \n\n"
                         end
                     else
@@ -132,9 +138,9 @@ class IframeParser < Parser
                         end
                         
                         if !ogImageURL.nil?
-                            result = "\r\n\r\n[![#{title}](#{ogImageURL} \"#{title}\")](#{ogURL})\r\n\r\n"
+                            result = "\r\n\r\n[![#{title}](#{ogImageURL} \"#{title}\")](#{ogURL})#{jekyllOpen}\r\n\r\n"
                         else
-                            result = "[#{title}](#{ogURL})"
+                            result = "[#{title}](#{ogURL})#{jekyllOpen}"
                         end
                     end
                 end

data/lib/Parsers/MIXTAPEEMBEDParser.rb

@@ -5,15 +5,24 @@ require "Parsers/Parser"
 require 'Models/Paragraph'
 
 class MIXTAPEEMBEDParser < Parser
-    attr_accessor :nextParser
+    attr_accessor :nextParser, :isForJekyll
+    
+    def initialize(isForJekyll)
+        @isForJekyll = isForJekyll
+    end
+
     def parse(paragraph)
         if paragraph.type == 'MIXTAPE_EMBED'
             if !paragraph.mixtapeMetadata.nil? && !paragraph.mixtapeMetadata.href.nil?
                 ogImageURL = Helper.fetchOGImage(paragraph.mixtapeMetadata.href)
                 if !ogImageURL.nil?
-                    "\r\n\r\n[![#{paragraph.text}](#{ogImageURL} \"#{paragraph.text}\")](#{paragraph.mixtapeMetadata.href})\r\n\r\n"
+                    jekyllOpen = ""
+                    if isForJekyll
+                        jekyllOpen = "{:target=\"_blank\"}"
+                    end
+                    "\r\n\r\n[![](#{ogImageURL})](#{paragraph.mixtapeMetadata.href})#{jekyllOpen}\r\n\r\n"
                 else
-                    "\n[#{paragraph.text}](#{paragraph.mixtapeMetadata.href})"
+                    "\n#{paragraph.text}"
                 end
             else
                 "\n#{paragraph.text}"

data/lib/Parsers/MarkupParser.rb

@@ -7,7 +7,7 @@ require 'securerandom'
 require 'User'
 
 class MarkupParser
-    attr_accessor :body, :paragraph, :isForJekyll
+    attr_accessor :body, :paragraph, :isForJekyll, :usersPostURLs
     
     def initialize(paragraph, isForJekyll)
         @paragraph = paragraph
@@ -18,7 +18,7 @@ class MarkupParser
         result = paragraph.text
         if !paragraph.markups.nil? && paragraph.markups.length > 0
             markupRender = MarkupStyleRender.new(paragraph, isForJekyll)
-
+            markupRender.usersPostURLs = usersPostURLs
             begin
                 result = markupRender.parse()
             rescue => e

data/lib/Parsers/MarkupStyleRender.rb

@@ -5,7 +5,7 @@ require 'Models/Paragraph'
 require 'Helper'
 
 class MarkupStyleRender 
-    attr_accessor :paragraph, :chars, :encodeType, :isForJekyll
+    attr_accessor :paragraph, :chars, :encodeType, :isForJekyll, :usersPostURLs
 
     class TextChar
         attr_accessor :chars, :type
@@ -171,11 +171,11 @@ class MarkupStyleRender
                 if markup.type == "EM"
                     tag = TagChar.new(2, markup.start, markup.end, "_", "_")
                 elsif markup.type == "CODE"
-                    tag = TagChar.new(3, markup.start, markup.end, "`", "`")
+                    tag = TagChar.new(0, markup.start, markup.end, "`", "`")
                 elsif markup.type == "STRONG"
                     tag = TagChar.new(2, markup.start, markup.end, "**", "**")
                 elsif markup.type == "ESCAPE"
-                    escapeTagChar = TagChar.new(0,markup.start, markup.end,'','')
+                    escapeTagChar = TagChar.new(999,markup.start, markup.end,'','')
                     escapeTagChar.startChars = TextChar.new('\\'.chars,'Text')
                     escapeTagChar.endChars = TextChar.new([],'Text')
 
@@ -188,7 +188,27 @@ class MarkupStyleRender
                         url = "https://medium.com/u/#{markup.userId}"
                     end
                     
-                    tag = TagChar.new(1, markup.start, markup.end, "[", "](#{url})")
+                    lastPath = url.split("/").last
+                    lastQuery = nil
+                    if !lastPath.nil?
+                        lastQuery = lastPath.split("-").last
+                    end
+                    
+                    if !usersPostURLs.nil? && !usersPostURLs.find { |usersPostURL| usersPostURL.split("/").last.split("-").last == lastQuery }.nil?
+                        if isForJekyll
+                            url = "(../#{lastQuery}/)"
+                        else
+                            url = "(#{lastPath})"
+                        end
+                    else
+                        if isForJekyll
+                            url = "(#{url}){:target=\"_blank\"}"
+                        else
+                            url = "(#{url})"
+                        end
+                    end
+
+                    tag = TagChar.new(1, markup.start, markup.end, "[", "]#{url}")
                 else
                     Helper.makeWarningText("Undefined Markup Type: #{markup.type}.")
                 end
@@ -205,6 +225,15 @@ class MarkupStyleRender
 
             chars.each do |index, char|
 
+                # is in code block
+                if !stack.last.nil? && stack.last.endChars.chars.join() == "`"
+                    containEndTag = tags.select { |tag| tag.endIndex == index && tag.endChars.chars.join() == "`" }.length > 0
+                    if !containEndTag 
+                        response.append(char)
+                        next
+                    end
+                end
+
                 if char.chars.join() == "\n"
                     brStack = stack.dup
                     while brStack.length > 0
@@ -228,21 +257,16 @@ class MarkupStyleRender
                 end
 
                 if char.chars.join() != "\n"
-                    if !stack.select { |tag| tag.startChars.chars.join() == "`" }.nil?
-                        # is in code block
-                        response.append(char)
-                    else
-                        resultChar = Helper.escapeMarkdown(char.chars.join())
-                        if isForJekyll 
-                            resultChar = Helper.escapeHTML(resultChar)
-                        end
-    
-                        response.append(TextChar.new(resultChar.chars, "Text"))
+                    resultChar = char.chars.join()
+                    if isForJekyll 
+                        resultChar = Helper.escapeHTML(resultChar)
                     end
+
+                    response.append(TextChar.new(resultChar.chars, "Text"))
                 end
 
                 endTags = tags.select { |tag| tag.endIndex == index }
-                if !endTags.nil? && endTags.length > 0
+                if endTags.length > 0
                     mismatchTags = []
                     while endTags.length > 0
                         stackTag = stack.pop
@@ -268,14 +292,14 @@ class MarkupStyleRender
                 tag = stack.pop
                 response.push(tag.endChars)
             end
-            
+
             response = optimize(response)
             result = response.map{ |response| response.chars }.join()
 
         else
             response = []
             chars.each do |index, char|
-                resultChar = escapeMarkdown(char)
+                resultChar = char
                 if isForJekyll 
                     resultChar = escapeHTML(char)
                 end

data/lib/Parsers/PQParser.rb

@@ -9,7 +9,7 @@ class PQParser < Parser
         if paragraph.type == 'PQ'
             result = "\r\n\r\n"
             paragraph.text.each_line do |p|
-                result += "> #{p}"
+                result += "> #{p} \n\n"
             end
             result += "\r\n\r\n"
 

data/lib/ZMediumFetcher.rb

@@ -19,7 +19,6 @@ require "Parsers/MarkupParser"
 require "Parsers/OLIParser"
 require "Parsers/MIXTAPEEMBEDParser"
 require "Parsers/PQParser"
-require "Parsers/LinkParser"
 require "Parsers/CodeBlockParser"
 
 require "PathPolicy"
@@ -30,7 +29,7 @@ require 'date'
 
 class ZMediumFetcher
 
-    attr_accessor :progress, :linkParser, :isForJekyll
+    attr_accessor :progress, :usersPostURLs, :isForJekyll
 
     class Progress
         attr_accessor :username, :postPath, :currentPostIndex, :totalPostsLength, :currentPostParagraphIndex, :totalPostParagraphsLength, :message
@@ -71,7 +70,7 @@ class ZMediumFetcher
 
     def initialize
         @progress = Progress.new()
-        @linkParser = LinkParser.new()
+        @usersPostURLs = nil
         @isForJekyll = false
     end
 
@@ -89,7 +88,7 @@ class ZMediumFetcher
             ppParser.setNext(uliParser)
         oliParser = OLIParser.new()
             uliParser.setNext(oliParser)
-        mixtapeembedParser = MIXTAPEEMBEDParser.new()
+        mixtapeembedParser = MIXTAPEEMBEDParser.new(isForJekyll)
             oliParser.setNext(mixtapeembedParser)
         pqParser = PQParser.new()
             mixtapeembedParser.setNext(pqParser)
@@ -223,8 +222,6 @@ class ZMediumFetcher
         progress.message = "Converting Post..."
         progress.printLog()
 
-        linkParser.isForJekyll = isForJekyll
-
         postWithDatePath = "#{postInfo.firstPublishedAt.strftime("%Y-%m-%d")}-#{postPath}"
 
         absolutePath = postPathPolicy.getAbsolutePath("#{postWithDatePath}.md")
@@ -236,7 +233,7 @@ class ZMediumFetcher
             if lines.first.start_with?("---")
                 dateLine = lines.select { |line| line.start_with?("last_modified_at:") }.first
                 if !dateLine.nil?
-                    fileLatestPublishedAt = Time.parse(dateLine[/^(last_modified_at:)\s+(\S*)/, 2]).to_i
+                    #fileLatestPublishedAt = Time.parse(dateLine[/^(last_modified_at:)\s+(\S*)/, 2]).to_i
                 end
             end
         end
@@ -260,12 +257,12 @@ class ZMediumFetcher
 
                     if !(CodeBlockParser.isCodeBlock(paragraph) || PREParser.isPRE(paragraph))
                         markupParser = MarkupParser.new(paragraph, isForJekyll)
+                        markupParser.usersPostURLs = usersPostURLs
                         paragraph.text = markupParser.parse()
                     end
 
                     result = startParser.parse(paragraph)
-                    result = linkParser.parse(result)
-                    
+
                     file.puts(result)
     
                     index += 1
@@ -274,7 +271,7 @@ class ZMediumFetcher
                     progress.printLog()
                 end
     
-                postWatermark = Helper.createWatermark(postURL)
+                postWatermark = Helper.createWatermark(postURL, isForJekyll)
                 if !postWatermark.nil?
                     file.puts(postWatermark)
                 end
@@ -311,7 +308,7 @@ class ZMediumFetcher
             nextID = postPageInfo["nextID"]
         end while !nextID.nil?
 
-        linkParser.usersPostURLs = postURLS
+        @usersPostURLs = postURLS
 
         progress.totalPostsLength = postURLS.length
         progress.currentPostIndex = 0

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ZMediumToMarkdown
 version: !ruby/object:Gem::Version
-  version: 2.0.5
+  version: 2.0.8
 platform: ruby
 authors:
 - ZhgChgLi
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-07-20 00:00:00.000000000 Z
+date: 2022-07-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -74,7 +74,6 @@ files:
 - lib/Parsers/H4Parser.rb
 - lib/Parsers/IMGParser.rb
 - lib/Parsers/IframeParser.rb
-- lib/Parsers/LinkParser.rb
 - lib/Parsers/MIXTAPEEMBEDParser.rb
 - lib/Parsers/MarkupParser.rb
 - lib/Parsers/MarkupStyleRender.rb

data/lib/Parsers/LinkParser.rb

@@ -1,54 +0,0 @@
-$lib = File.expand_path('../', File.dirname(__FILE__))
-
-require 'Models/Paragraph'
-
-class LinkParser
-    attr_accessor :usersPostURLs, :isForJekyll
-
-    def initialize()
-        @usersPostURLs = []
-        @isForJekyll = false
-    end
-
-    def parse(markdownString)
-        matchLinks = markdownString.scan(/\[[^\]]*\]\(([^\)]+)\)/m)
-        if !matchLinks.nil?
-
-            matchLinks.each do |matchLink|
-                link = matchLink[0]
-                linkMarkdown = "(#{link})"
-                newLinkMarkdown = linkMarkdown
-
-                if isForJekyll
-                    newLinkMarkdown = "(#{link}){:target=\"_blank\"}"
-                end
-                
-
-                if !usersPostURLs.nil?
-                    # if have provide user's post urls
-                    # find & replace medium url to local post url if matched
-
-                    if isForJekyll
-                        postPath = link.split("/").last.split("-").last
-                    else
-                        postPath = link.split("/").last
-                    end
-                    
-                    if !usersPostURLs.find { |usersPostURL| usersPostURL.split("/").last.split("-").last == postPath.split("-").last }.nil?
-                        if isForJekyll
-                            newLinkMarkdown = "(../#{postPath}/)"
-                        else
-                            newLinkMarkdown = "(#{postPath})"
-                        end
-                    end
-                end
-
-                if linkMarkdown != newLinkMarkdown
-                    markdownString = markdownString.sub! linkMarkdown, newLinkMarkdown
-                end
-            end
-        end
-
-        markdownString
-    end
-end