ZMediumToMarkdown 1.6.1 → 1.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 92b412153da4daf0a7594c1558a847412863405eec14da02325984a22bc855a8
-  data.tar.gz: ccdf1c0e166323323f55b91fc0991b3eae1da0ad070e2b884b3b30266661c03b
+  metadata.gz: ff9b27bae7ac1365701ccb1b3174a8b7a2d3b7b2fa12771d10665368636c1733
+  data.tar.gz: 0f68f9aca2a902694898560c82b689bc10b0e45d6c2d181b279002fb263f74d4
 SHA512:
-  metadata.gz: 120c75b800992a2a815c058430326f6b279f52f08ba4484465fdf7eca31b8460f1170bdd30956c1bfd771a3fbb0d5763a21e9327530e80e76250d52551a4ec9f
-  data.tar.gz: ffb13239eabe2a6f302a093dfea6309eaaaa3eee0ffb960ee9798f96969c922de6a287b3c8ac47aca1c8b4af2f51adcc52bdf2470e59f8cf12420338a03e019b
+  metadata.gz: a397b8860995b6fe0e7f4aea405c352d5ce05de20de0d9dc041001bc8af3c8509ac01387f5ea7ae5ecedc844ba41e70ade1ac6f6f58d4d9baca02cce0783c28d
+  data.tar.gz: 532bcf53a46474d897bb27dcdfe3153dfd3103cc43de01a9588608776284ddb0f23f89e836797bf453469168c38ed041a1c63f1a607c0b16616bafd002df75f1

data/bin/ZMediumToMarkdown

@@ -14,18 +14,35 @@ class Main
         ARGV << '-h' if ARGV.empty?
 
         filePath = ENV['PWD'] || ::Dir.pwd
-        outputFilePath = PathPolicy.new(filePath, "Output")
 
         OptionParser.new do |opts|
             opts.banner = "Usage: ZMediumFetcher [options]"
         
             opts.on('-uUSERNAME', '--username=USERNAME', 'Downloading all posts from user') do |username|
+                outputFilePath = PathPolicy.new(filePath, "/")
                 fetcher.downloadPostsByUsername(username, outputFilePath)
 
                 Helper.printNewVersionMessageIfExists()
             end
         
             opts.on('-pPOST_URL', '--postURL=POST_URL', 'Downloading single post') do |postURL|
+                outputFilePath = PathPolicy.new(filePath, "/")
+                fetcher.downloadPost(postURL, outputFilePath)
+
+                Helper.printNewVersionMessageIfExists()
+            end
+
+            opts.on('-jUSERNAME', '--jekyllUsername=USERNAME', 'Downloading all posts from user with Jekyll friendly') do |username|
+                outputFilePath = PathPolicy.new(filePath, "Output")
+                fetcher.isForJekyll = true
+                fetcher.downloadPostsByUsername(username, outputFilePath)
+
+                Helper.printNewVersionMessageIfExists()
+            end
+        
+            opts.on('-kpPOST_URL', '--jekyllPostURL=POST_URL', 'Downloading single post with Jekyll friendly') do |postURL|
+                outputFilePath = PathPolicy.new(filePath, "Output")
+                fetcher.isForJekyll = true
                 fetcher.downloadPost(postURL, outputFilePath)
 
                 Helper.printNewVersionMessageIfExists()

data/lib/Helper.rb

@@ -159,17 +159,7 @@ class Helper
     end
 
         
-    def self.createWatermark(postURL)
-        text = "\r\n\r\n\r\n"
-        text += "+-----------------------------------------------------------------------------------+"
-        text += "\r\n"
-        text += "\r\n"
-        text += "| **[View original post on Medium](#{postURL}) - Converted by [ZhgChgLi](https://blog.zhgchg.li)/[ZMediumToMarkdown](https://github.com/ZhgChgLi/ZMediumToMarkdown)** |"
-        text += "\r\n"
-        text += "\r\n"
-        text += "+-----------------------------------------------------------------------------------+"
-        text += "\r\n"
-        
-        text
+    def self.createWatermark(postURL)        
+        text = "\r\n[Medium 原文](#{postURL})"
     end
-end
+end

data/lib/Parsers/CodeBlockParser.rb

@@ -10,8 +10,16 @@ class CodeBlockParser < Parser
         'CODE_BLOCK'
     end
 
+    def self.isCodeBlock(paragraph)
+        if paragraph.nil? 
+            false
+        else
+            paragraph.type == CodeBlockParser.getTypeString()
+        end
+    end
+
     def parse(paragraph)
-        if paragraph.type == CodeBlockParser.getTypeString()
+        if CodeBlockParser.isCodeBlock(paragraph)
             "```\n#{paragraph.text}\n```"
         else
             if !nextParser.nil?

data/lib/Parsers/IMGParser.rb

@@ -7,7 +7,12 @@ require 'ImageDownloader'
 require 'PathPolicy'
 
 class IMGParser < Parser
-    attr_accessor :nextParser, :pathPolicy
+    attr_accessor :nextParser, :pathPolicy, :isForJekyll
+    
+    def initialize(isForJekyll)
+        @isForJekyll = isForJekyll
+    end
+
     def parse(paragraph)
         if paragraph.type == 'IMG'
 
@@ -25,9 +30,13 @@ class IMGParser < Parser
 
             if  ImageDownloader.download(absolutePath, imageURL)
                 relativePath = "#{pathPolicy.getRelativePath(nil)}/#{imagePathPolicy.getRelativePath(fileName)}"
-                "![#{paragraph.text}](/#{relativePath}#{comment})"
+                if isForJekyll
+                    "\r\n![#{paragraph.text}](/#{relativePath}#{comment})\r\n"
+                else
+                    "\r\n![#{paragraph.text}](#{relativePath}#{comment})\r\n"
+                end
             else
-                "![#{paragraph.text}](#{imageURL}#{comment})"
+                "\r\n![#{paragraph.text}](#{imageURL}#{comment})\r\n"
             end
         else
             if !nextParser.nil?

data/lib/Parsers/IframeParser.rb

@@ -11,7 +11,12 @@ require 'ImageDownloader'
 require 'PathPolicy'
 
 class IframeParser < Parser
-    attr_accessor :nextParser, :pathPolicy
+    attr_accessor :nextParser, :pathPolicy, :isForJekyll
+
+    def initialize(isForJekyll)
+        @isForJekyll = isForJekyll
+    end
+
     def parse(paragraph)
         if paragraph.type == 'IFRAME'
             if !paragraph.iframe.src.nil? && paragraph.iframe.src != ""
@@ -35,9 +40,13 @@ class IframeParser < Parser
                     title = paragraph.iframe.title
                     if  ImageDownloader.download(absolutePath, imageURL)
                         relativePath = "#{pathPolicy.getRelativePath(nil)}/#{imagePathPolicy.getRelativePath(fileName)}"
-                        result = "\n[![#{title}](#{relativePath} \"#{title}\")](#{params["url"]})"
+                        if isForJekyll
+                            result = "\r\n[![#{title}](/#{relativePath} \"#{title}\")](#{params["url"]})\r\n"
+                        else
+                            result = "\r\n[![#{title}](#{relativePath} \"#{title}\")](#{params["url"]})\r\n"
+                        end
                     else
-                        result = "\n[#{title}](#{params["url"]})"
+                        result = "\r\n[#{title}](#{params["url"]})\r\n"
                     end
                 end
             else

data/lib/Parsers/LinkParser.rb

@@ -3,10 +3,11 @@ $lib = File.expand_path('../', File.dirname(__FILE__))
 require 'Models/Paragraph'
 
 class LinkParser
-    attr_accessor :usersPostURLs
+    attr_accessor :usersPostURLs, :isForJekyll
 
-    def initialize(usersPostURLs)
+    def initialize(usersPostURLs, isForJekyll)
         @usersPostURLs = usersPostURLs
+        @isForJekyll = isForJekyll
     end
 
     def parse(markdownString, markupLinks)
@@ -21,20 +22,17 @@ class LinkParser
                         # if have provide user's post urls
                         # find & replace medium url to local post url if matched
 
-                        postPath = link.split("/").last
-                        if !usersPostURLs.find { |usersPostURL| usersPostURL.split("/").last.split("-").last == postPath.split("-").last }.nil?
-                            markdownString = markdownString.sub! link, postPath
+                        if isForJekyll
+                            postPath = link.split("/").last.split("-").last
+                        else
+                            postPath = link.split("/").last
                         end
-                    else
-                        if !(link =~ /\A#{URI::regexp(['http', 'https'])}\z/)
-                            # medium will give you an relative path if url is medium's post (due to we use html to markdown render)
-                            # e.g. /zrealm-ios-dev/visitor-pattern-in-ios-swift-ba5773a7bfea
-                            # it's not a vaild url
-    
-                            # fullfill url from markup attribute
-                            match = markupLinks.find{ |markupLink| markupLink.include? link }
-                            if !match.nil?
-                                markdownString = markdownString.sub! link, match
+                        
+                        if !usersPostURLs.find { |usersPostURL| usersPostURL.split("/").last.split("-").last == postPath.split("-").last }.nil?
+                            if isForJekyll
+                                markdownString = markdownString.sub! link, "../#{postPath}"
+                            else
+                                markdownString = markdownString.sub! link, "#{postPath}"
                             end
                         end
                     end

data/lib/Parsers/MarkupStyleRender.rb

@@ -32,12 +32,10 @@ class MarkupStyleRender
         chars = {}
         index = 0
         
-        emojiRegex = /[\u{203C}\u{2049}\u{20E3}\u{2122}\u{2139}\u{2194}-\u{2199}\u{21A9}-\u{21AA}\u{231A}-\u{231B}\u{23E9}-\u{23EC}\u{23F0}\u{23F3}\u{24C2}\u{25AA}-\u{25AB}\u{25B6}\u{25C0}\u{25FB}-\u{25FE}\u{2600}-\u{2601}\u{260E}\u{2611}\u{2614}-\u{2615}\u{261D}\u{263A}\u{2648}-\u{2653}\u{2660}\u{2663}\u{2665}-\u{2666}\u{2668}\u{267B}\u{267F}\u{2693}\u{26A0}-\u{26A1}\u{26AA}-\u{26AB}\u{26BD}-\u{26BE}\u{26C4}-\u{26C5}\u{26CE}\u{26D4}\u{26EA}\u{26F2}-\u{26F3}\u{26F5}\u{26FA}\u{26FD}\u{2702}\u{2705}\u{2708}-\u{270C}\u{270F}\u{2712}\u{2714}\u{2716}\u{2728}\u{2733}-\u{2734}\u{2744}\u{2747}\u{274C}\u{274E}\u{2753}-\u{2755}\u{2757}\u{2764}\u{2795}-\u{2797}\u{27A1}\u{27B0}\u{2934}-\u{2935}\u{2B05}-\u{2B07}\u{2B1B}-\u{2B1C}\u{2B50}\u{2B55}\u{3030}\u{303D}\u{3297}\u{3299}\u{1F004}\u{1F0CF}\u{1F170}-\u{1F171}\u{1F17E}-\u{1F17F}\u{1F18E}\u{1F191}-\u{1F19A}\u{1F1E7}-\u{1F1EC}\u{1F1EE}-\u{1F1F0}\u{1F1F3}\u{1F1F5}\u{1F1F7}-\u{1F1FA}\u{1F201}-\u{1F202}\u{1F21A}\u{1F22F}\u{1F232}-\u{1F23A}\u{1F250}-\u{1F251}\u{1F300}-\u{1F320}\u{1F330}-\u{1F335}\u{1F337}-\u{1F37C}\u{1F380}-\u{1F393}\u{1F3A0}-\u{1F3C4}\u{1F3C6}-\u{1F3CA}\u{1F3E0}-\u{1F3F0}\u{1F400}-\u{1F43E}\u{1F440}\u{1F442}-\u{1F4F7}\u{1F4F9}-\u{1F4FC}\u{1F500}-\u{1F507}\u{1F509}-\u{1F53D}\u{1F550}-\u{1F567}\u{1F5FB}-\u{1F640}\u{1F645}-\u{1F64F}\u{1F680}-\u{1F68A}]/
-        excludesEmojis = ["⚠"]
         paragraph.text.each_char do |char|
             chars[index] = TextChar.new([char], "Text")
             index += 1
-            if char =~ emojiRegex && !excludesEmojis.include?(char)
+            if char.bytes.length >= 4
                 # some emoji need more space (in Medium)
                 chars[index] = TextChar.new([], "Text")
                 index += 1

data/lib/ZMediumFetcher.rb

@@ -30,7 +30,7 @@ require 'date'
 
 class ZMediumFetcher
 
-    attr_accessor :progress, :linkParser
+    attr_accessor :progress, :linkParser, :isForJekyll
 
     class Progress
         attr_accessor :username, :postPath, :currentPostIndex, :totalPostsLength, :currentPostParagraphIndex, :totalPostParagraphsLength, :message
@@ -71,7 +71,8 @@ class ZMediumFetcher
 
     def initialize
         @progress = Progress.new()
-        @linkParser = LinkParser.new(nil)
+        @linkParser = LinkParser.new(nil, false)
+        @isForJekyll = false
     end
 
     def buildParser(imagePathPolicy)
@@ -92,10 +93,10 @@ class ZMediumFetcher
             oliParser.setNext(mixtapeembedParser)
         pqParser = PQParser.new()
             mixtapeembedParser.setNext(pqParser)
-        iframeParser = IframeParser.new()
+        iframeParser = IframeParser.new(isForJekyll)
         iframeParser.pathPolicy = imagePathPolicy
             pqParser.setNext(iframeParser)
-        imgParser = IMGParser.new()
+        imgParser = IMGParser.new(isForJekyll)
         imgParser.pathPolicy = imagePathPolicy
             iframeParser.setNext(imgParser)
         bqParser = BQParser.new()
@@ -113,7 +114,12 @@ class ZMediumFetcher
 
     def downloadPost(postURL, pathPolicy)
         postID = Post.getPostIDFromPostURLString(postURL)
-        postPath = Post.getPostPathFromPostURLString(postURL)
+
+        if isForJekyll
+            postPath = postID # use only post id is more friendly for url seo
+        else
+            postPath = Post.getPostPathFromPostURLString(postURL)
+        end
 
         progress.postPath = postPath
         progress.message = "Downloading Post..."
@@ -203,9 +209,14 @@ class ZMediumFetcher
             previousParagraph = paragraph
         end
 
-        postPathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath(nil), "posts")
-
-        imagePathPolicy = PathPolicy.new(postPathPolicy.getAbsolutePath(nil), "assets")
+        if isForJekyll
+            postPathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath(nil), "_posts")
+            imagePathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath(nil), "assets")
+        else
+            postPathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath(nil), "posts")
+            imagePathPolicy = PathPolicy.new(postPathPolicy.getAbsolutePath(nil), "assets")
+        end
+        
         startParser = buildParser(imagePathPolicy)
 
         progress.totalPostParagraphsLength = paragraphs.length
@@ -231,13 +242,21 @@ class ZMediumFetcher
                 
                 index = 0
                 paragraphs.each do |paragraph|
-                    markupParser = MarkupParser.new(paragraph)
-                    paragraph.text = markupParser.parse()
+
+                    if !(CodeBlockParser.isCodeBlock(paragraph) || PREParser.isPRE(paragraph))
+                        markupParser = MarkupParser.new(paragraph)
+                        paragraph.text = markupParser.parse()
+                    end
+
                     result = startParser.parse(paragraph)
     
                     if !linkParser.nil?
                         result = linkParser.parse(result, paragraph.markupLinks)
                     end
+
+                    if paragraph.orgText == "延伸閱讀" or result.include? "Like Z Realm" or paragraph.orgText == "有任何問題及指教歡迎與我聯絡。"
+                        break
+                    end
                     
                     file.puts(result)
     
@@ -281,7 +300,7 @@ class ZMediumFetcher
             nextID = postPageInfo["nextID"]
         end while !nextID.nil?
 
-        @linkParser = LinkParser.new(postURLS)
+        @linkParser = LinkParser.new(postURLS, isForJekyll)
 
         progress.totalPostsLength = postURLS.length
         progress.currentPostIndex = 0

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ZMediumToMarkdown
 version: !ruby/object:Gem::Version
-  version: 1.6.1
+  version: 1.7.0
 platform: ruby
 authors:
 - ZhgChgLi
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-06-07 00:00:00.000000000 Z
+date: 2022-06-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri