ZMediumToMarkdown 2.0.0 → 2.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 796d995f3d5f3f1edf3de599a28df4a8bea5ab9083d9bf8191d0d0535c924eb3
-  data.tar.gz: 7fa92c888507d4fea9293a3649c1656d3891a04b34d73d035d1a65676a5c8dc4
+  metadata.gz: c410145d7924db7410198b57030d8a886b81162d2dc0f63c580d9140131aaae3
+  data.tar.gz: 91930b43c92725becb2d6f2e2246a4df6c2bed1d7616cd4f6dfb11cafa0d3af3
 SHA512:
-  metadata.gz: 434c7f737e281189a0feaa821d25e936632be3e72731a495ba62ea945bfef67063518637879b44ecf5f9121ce4ae8b302553bca55959a93e874904cc0fddc808
-  data.tar.gz: 298efd510208b800826cd39be456e47a7b1744291078fd7e61b954a59e9c9257e796c09ed1813b098ad0c8615c17b1b7e19217388dcbcd9f085d9b5151a35663
+  metadata.gz: b23e795f4af879ad6902dcf7a842cb0f1ad160e722196b1e8e4b17bb404686ac0f9fb3801b396124e4f248beb4743c1c56787bf5ef17fecb1b662f880983ce74
+  data.tar.gz: 9fa9954456a922437b624e2b4a762b509e5fac44ba453ca947b87ab838ad0110fd005cb628e9ae8042d2ddf60f0b850e92a08a8a9a148c0a00e8c30c77326670

data/bin/ZMediumToMarkdown

@@ -19,21 +19,21 @@ class Main
             opts.banner = "Usage: ZMediumFetcher [options]"
         
             opts.on('-uUSERNAME', '--username=USERNAME', 'Downloading all posts from user') do |username|
-                outputFilePath = PathPolicy.new(filePath, "Output")
+                outputFilePath = PathPolicy.new("#{filePath}/Output", "Output")
                 fetcher.downloadPostsByUsername(username, outputFilePath)
 
                 Helper.printNewVersionMessageIfExists()
             end
         
             opts.on('-pPOST_URL', '--postURL=POST_URL', 'Downloading single post') do |postURL|
-                outputFilePath = PathPolicy.new(filePath, "Output")
+                outputFilePath = PathPolicy.new("#{filePath}/Output", "Output")
                 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, "/")
+                outputFilePath = PathPolicy.new(filePath, "")
                 fetcher.isForJekyll = true
                 fetcher.downloadPostsByUsername(username, outputFilePath)
 
@@ -41,7 +41,7 @@ class Main
             end
         
             opts.on('-kPOST_URL', '--jekyllPostURL=POST_URL', 'Downloading single post with Jekyll friendly') do |postURL|
-                outputFilePath = PathPolicy.new(filePath, "/")
+                outputFilePath = PathPolicy.new(filePath, "")
                 fetcher.isForJekyll = true
                 fetcher.downloadPost(postURL, outputFilePath)
 

data/lib/Helper.rb

@@ -12,10 +12,6 @@ require 'nokogiri'
 
 class Helper
 
-    def self.escapeMarkdown(text)
-        text.gsub(/(\*|_|`|\||\\|\{|\}|\[|\]|\(|\)|#|\+|\-|\.|\!)/){ |x| "\\#{x}" }
-    end
-
     def self.fetchOGImage(url)
         html = Request.html(Request.URL(url))
         content = html.search("meta[property='og:image']").attribute('content')
@@ -99,30 +95,28 @@ class Helper
     end
 
     def self.createPostInfo(postInfo, isForJekyll)
+        title = postInfo.title.gsub("[","")
+        title = title.gsub("]","")
+
+        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 += "categories: #{postInfo.collectionName}\n"
+        result += "tags: [#{postInfo.tags.join(",")}]\n"
+        result += "description: #{postInfo.description}\n"
+        if !postInfo.previewImage.nil?
+            result += "image:\r\n"
+            result += "  path: #{postInfo.previewImage}\r\n"
+        end
         if isForJekyll
-            title = postInfo.title.gsub("[","")
-            title = title.gsub("]","")
-
-            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 += "categories: #{postInfo.collectionName}\n"
-            result += "tags: [#{postInfo.tags.join(",")}]\n"
-            result += "description: #{postInfo.description}\n"
-            if !postInfo.previewImage.nil?
-                result += "image:\r\n"
-                result += "  path: #{postInfo.previewImage}\r\n"
-            end
             result += "render_with_liquid: false\n"
-
-            result += "---\n"
-            result += "\r\n"
-
-            result
-        else
-            nil
         end
+        result += "---\n"
+        result += "\r\n"
+
+        result
     end
 
     def self.printNewVersionMessageIfExists() 

data/lib/Models/Paragraph.rb

@@ -5,7 +5,7 @@ require 'Parsers/PParser'
 require 'securerandom'
 
 class Paragraph
-    attr_accessor :postID, :name, :orgText, :orgTextWithEscape, :text, :type, :href, :metadata, :mixtapeMetadata, :iframe, :oliIndex, :markups, :markupLinks
+    attr_accessor :postID, :name, :orgText, :text, :type, :href, :metadata, :mixtapeMetadata, :iframe, :oliIndex, :markups, :markupLinks
 
     class Iframe
         attr_accessor :id, :title, :type, :src
@@ -66,9 +66,6 @@ class Paragraph
         @href = json['href']
         @postID = postID
 
-        orgTextWithEscape = Helper.escapeMarkdown(json['text'])
-        @orgTextWithEscape = orgTextWithEscape
-
         if json['metadata'].nil?
             @metadata = nil
         else
@@ -87,19 +84,28 @@ class Paragraph
             @iframe = Iframe.new(json['iframe']['mediaResource'])
         end
         
+        markups = []
         if !json['markups'].nil? && json['markups'].length > 0
-            markups = []
             json['markups'].each do |markup|
                 markups.append(Markup.new(markup))
             end
-            @markups = markups
-
+            
             links = json['markups'].select{ |markup| markup["type"] == "A" }
             if !links.nil? && links.length > 0
                 @markupLinks = links.map{ |link| link["href"] }
             end
-        else
-            @markups = nil
         end
+
+        i = 0
+        while i = orgText.index(/(\*|_|`|\||\\|\{|\}|\[|\]|\(|\)|#|\+|\-|\.|\!)/, i + 1)
+            escapeMarkup = {
+                "type" => 'ESCAPE',
+                "start" => i,
+                "end" => i + 1
+            }
+            markups.append(Markup.new(escapeMarkup))
+        end
+
+        @markups = markups
     end
 end

data/lib/Parsers/IMGParser.rb

@@ -20,24 +20,21 @@ class IMGParser < Parser
 
             imageURL = "https://miro.medium.com/max/1400/#{fileName}"
 
-            imagePathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath(nil), paragraph.postID)
+            imagePathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath(paragraph.postID), pathPolicy.getRelativePath(paragraph.postID))
             absolutePath = imagePathPolicy.getAbsolutePath(fileName)
             
             result = ""
             alt = ""
-            if paragraph.orgTextWithEscape != "" 
-                alt = " \"#{paragraph.orgTextWithEscape}\""
-            end
 
             if  ImageDownloader.download(absolutePath, imageURL)
-                relativePath = "#{pathPolicy.getRelativePath(nil)}/#{imagePathPolicy.getRelativePath(fileName)}"
+                relativePath = imagePathPolicy.getRelativePath(fileName)
                 if isForJekyll
-                    result = "\r\n\r\n![#{paragraph.orgTextWithEscape}](/#{relativePath}#{alt})\r\n\r\n"
+                    result = "\r\n\r\n![#{paragraph.text}](/#{relativePath}#{alt})\r\n\r\n"
                 else
-                    result = "\r\n\r\n![#{paragraph.orgTextWithEscape}](#{relativePath}#{alt})\r\n\r\n"
+                    result = "\r\n\r\n![#{paragraph.text}](#{relativePath}#{alt})\r\n\r\n"
                 end
             else
-                result = "\r\n\r\n![#{paragraph.orgTextWithEscape}](#{imageURL}#{alt})\r\n\r\n"
+                result = "\r\n\r\n![#{paragraph.text}](#{imageURL}#{alt})\r\n\r\n"
             end
 
             if paragraph.text != ""

data/lib/Parsers/IframeParser.rb

@@ -39,7 +39,7 @@ class IframeParser < Parser
                     fileName = "#{paragraph.name}_#{URI(params["image"]).path.split("/").last}" #21de_default.jpg
 
                     imageURL = params["image"]
-                    imagePathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath(nil), paragraph.postID)
+                    imagePathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath(paragraph.postID), pathPolicy.getRelativePath(paragraph.postID))
                     absolutePath = imagePathPolicy.getAbsolutePath(fileName)
                     title = paragraph.iframe.title
                     if title.nil? or title == ""
@@ -47,7 +47,7 @@ class IframeParser < Parser
                     end
 
                     if  ImageDownloader.download(absolutePath, imageURL)
-                        relativePath = "#{pathPolicy.getRelativePath(nil)}/#{imagePathPolicy.getRelativePath(fileName)}"
+                        relativePath = imagePathPolicy.getRelativePath(fileName)
                         if isForJekyll
                             result = "\r\n\r\n[![#{title}](/#{relativePath} \"#{title}\")](#{params["url"]})\r\n\r\n"
                         else

data/lib/Parsers/MIXTAPEEMBEDParser.rb

@@ -11,9 +11,9 @@ class MIXTAPEEMBEDParser < Parser
             if !paragraph.mixtapeMetadata.nil? && !paragraph.mixtapeMetadata.href.nil?
                 ogImageURL = Helper.fetchOGImage(paragraph.mixtapeMetadata.href)
                 if !ogImageURL.nil?
-                    "\r\n\r\n[![#{paragraph.orgTextWithEscape}](#{ogImageURL} \"#{paragraph.orgTextWithEscape}\")](#{paragraph.mixtapeMetadata.href})\r\n\r\n"
+                    "\r\n\r\n[![#{paragraph.text}](#{ogImageURL} \"#{paragraph.text}\")](#{paragraph.mixtapeMetadata.href})\r\n\r\n"
                 else
-                    "\n[#{paragraph.orgTextWithEscape}](#{paragraph.mixtapeMetadata.href})"
+                    "\n[#{paragraph.text}](#{paragraph.mixtapeMetadata.href})"
                 end
             else
                 "\n#{paragraph.text}"

data/lib/Parsers/MarkupStyleRender.rb

@@ -174,6 +174,8 @@ class MarkupStyleRender
                     tag = TagChar.new(3, markup.start, markup.end, "`", "`")
                 elsif markup.type == "STRONG"
                     tag = TagChar.new(2, markup.start, markup.end, "**", "**")
+                elsif markup.type == "ESCAPE"
+                    tag = TagChar.new(2, markup.start, markup.end, "\\", "**")
                 elsif markup.type == "A"
                     url = markup.href
                     if markup.anchorType == "LINK"

data/lib/PathPolicy.rb

@@ -8,18 +8,29 @@ class PathPolicy
     end
 
     def getRelativePath(lastPath)
-        if lastPath.nil?
-            "#{path}"
-        else
-            "#{path}/#{lastPath}"
+        result = path
+
+        if result != ""
+            result += "/"
+        end
+
+        if !lastPath.nil?
+            result += lastPath
         end
+
+        result
     end
 
     def getAbsolutePath(lastPath)
-        if lastPath.nil?
-            "#{rootPath}/#{path}"
-        else
-            "#{rootPath}/#{path}/#{lastPath}"
+        result = rootPath        
+
+        if !lastPath.nil?
+            if result != ""
+                result += "/"
+            end
+            result += "#{lastPath}"
         end
+
+        result
     end
 end

data/lib/Post.rb

@@ -70,13 +70,14 @@ class Post
     if !previewImage.nil?
       previewImageFIleName = content&.dig(previewImage, "id")
 
-      imagePathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath(nil), postID)
+      imagePathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath(postID), pathPolicy.getRelativePath(postID))
+      
       absolutePath = imagePathPolicy.getAbsolutePath(previewImageFIleName)
 
       imageURL = "https://miro.medium.com/max/1400/#{previewImageFIleName}"
 
       if  ImageDownloader.download(absolutePath, imageURL)
-          relativePath = "#{pathPolicy.getRelativePath(nil)}/#{imagePathPolicy.getRelativePath(previewImageFIleName)}"
+          relativePath = imagePathPolicy.getRelativePath(previewImageFIleName)
           postInfo.previewImage = relativePath
       end
     end

data/lib/ZMediumFetcher.rb

@@ -122,11 +122,11 @@ class ZMediumFetcher
         end
 
         if isForJekyll
-            postPathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath(nil), "_posts/zmediumtomarkdown")
-            imagePathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath(nil), "assets")
+            postPathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath("_posts/zmediumtomarkdown"), pathPolicy.getRelativePath("_posts/zmediumtomarkdown"))
+            imagePathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath("assets"), "assets")
         else
-            postPathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath(nil), "zmediumtomarkdown")
-            imagePathPolicy = PathPolicy.new(postPathPolicy.getAbsolutePath(nil), "assets")
+            postPathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath("zmediumtomarkdown"), pathPolicy.getRelativePath("zmediumtomarkdown"))
+            imagePathPolicy = PathPolicy.new(postPathPolicy.getAbsolutePath("assets"), "assets")
         end
 
         progress.postPath = postPath
@@ -229,8 +229,19 @@ class ZMediumFetcher
 
         absolutePath = postPathPolicy.getAbsolutePath("#{postWithDatePath}.md")
         
-        # if markdown file is exists and last modification time is >= latestPublishedAt(last update post time on medium)
-        if File.file?(absolutePath) && File.mtime(absolutePath).to_time.to_i >= postInfo.latestPublishedAt.to_i
+        fileLatestPublishedAt = nil
+
+        if File.file?(absolutePath)
+            lines = File.foreach(absolutePath).first(15)
+            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
+                end
+            end
+        end
+
+        if !fileLatestPublishedAt.nil? && fileLatestPublishedAt >= postInfo.latestPublishedAt.to_i
             # Already downloaded and nothing has changed!, Skip!
             progress.currentPostParagraphIndex = paragraphs.length
             progress.message = "Skip, Post already downloaded and nothing has changed!"
@@ -310,7 +321,7 @@ class ZMediumFetcher
         if isForJekyll
             downloadPathPolicy = pathPolicy
         else
-            downloadPathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath(nil), "users/#{username}")
+            downloadPathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath("users/#{username}"), pathPolicy.getRelativePath("users/#{username}"))
         end
        
         index = 0

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ZMediumToMarkdown
 version: !ruby/object:Gem::Version
-  version: 2.0.0
+  version: 2.0.1
 platform: ruby
 authors:
 - ZhgChgLi
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-07-18 00:00:00.000000000 Z
+date: 2022-07-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri