ZMediumToMarkdown 1.6.0 → 1.6.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6026b5ebd732b82696ca5a7de549e5167067336998152c8a5e7bed751d610b78
-  data.tar.gz: 76c24779eaceb1763225f6e5e274fb5177685b0be9f75390ce189ec047278c21
+  metadata.gz: a289a9d9178f9001eb97db354501e6112331be901a629719c775a28098268cc9
+  data.tar.gz: f116778fbd8a33287c289a905eb9026620f6d601953446cf946858ed3d108576
 SHA512:
-  metadata.gz: db56b44ece9656eb90f703a6416c54a163f54e0208981ebf37029af9491fb39e30252b564e5d63f6defc63c72c51f3c3f944f531dfbd77ed10ba06b59abbd511
-  data.tar.gz: b71cc148ded49d5e3bd1ab8e72d915a5b8716de041cba43d39158fd47f451ce4c52ad0d671462a3dca7571879c744fa029b0af7a7e45d2fea92788d5ee858f0b
+  metadata.gz: c4efcdb20c64941fc5b800c4029088179a65e0298a78a21ee68d6a967738a487395948cade619dd6420e075c882df5744373e7c661e7d47cc92b5a3ac1e8722b
+  data.tar.gz: 133737ccac50e0d5cddac1ea10ef10cb6e46ca972a195160b6451a04f38d6a18171fd62849769ad159bbd227614495fe4a6d7c59b5a0d60892cb0373f44b5b16

data/lib/Helper.rb

@@ -77,10 +77,15 @@ class Helper
     end
 
     def self.createPostInfo(postInfo)
+
+        title = postInfo.title.gsub("[","")
+        title = title.gsub("]","")
+
         result = "---\n"
-        result += "title: #{postInfo.title}\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 += "---\n"
         result += "\r\n"
@@ -159,7 +164,7 @@ class Helper
         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 += "| **[View original post on Medium](#{postURL}) - Converted by [ZhgChgLi](https://zhgchg.li)/[ZMediumToMarkdown](https://github.com/ZhgChgLi/ZMediumToMarkdown)** |"
         text += "\r\n"
         text += "\r\n"
         text += "+-----------------------------------------------------------------------------------+"
@@ -167,4 +172,4 @@ class Helper
         
         text
     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

@@ -18,11 +18,16 @@ class IMGParser < Parser
             imagePathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath(nil), paragraph.postID)
             absolutePath = imagePathPolicy.getAbsolutePath(fileName)
             
+            comment = ""
+            if paragraph.text != ""
+                comment = " \"#{paragraph.text}\""
+            end
+
             if  ImageDownloader.download(absolutePath, imageURL)
                 relativePath = "#{pathPolicy.getRelativePath(nil)}/#{imagePathPolicy.getRelativePath(fileName)}"
-                "![#{paragraph.text}](#{relativePath} \"#{paragraph.text}\")"
+                "\r\n![#{paragraph.text}](#{relativePath}#{comment})\r\n"
             else
-                "![#{paragraph.text}](#{imageURL} \"#{paragraph.text}\")"
+                "\r\n![#{paragraph.text}](#{imageURL}#{comment})\r\n"
             end
         else
             if !nextParser.nil?

data/lib/Parsers/IframeParser.rb

@@ -35,9 +35,9 @@ 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"]})"
+                        result = "\r\n[![#{title}](#{relativePath} \"#{title}\")](#{params["url"]})\r\n"
                     else
-                        result = "\n[#{title}](#{params["url"]})"
+                        result = "\r\n[#{title}](#{params["url"]})\r\n"
                     end
                 end
             else
@@ -55,7 +55,7 @@ class IframeParser < Parser
                     gistHTML.search('a').each do |a|
                         if a.text == 'view raw'
                             gistRAW = Request.body(Request.URL(a['href']))
-                            result = "```#{lang}\n#{gistRAW}\n```"
+                            result = "```#{lang.downcase}\n#{gistRAW}\n```"
                         end
                     end
                 end

data/lib/Parsers/LinkParser.rb

@@ -23,19 +23,7 @@ class LinkParser
 
                         postPath = link.split("/").last
                         if !usersPostURLs.find { |usersPostURL| usersPostURL.split("/").last.split("-").last == postPath.split("-").last }.nil?
-                            markdownString = markdownString.sub! link, postPath
-                        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
-                            end
+                            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/Post.rb

@@ -9,7 +9,7 @@ require 'date'
 class Post
 
   class PostInfo
-    attr_accessor :title, :tags, :creator, :firstPublishedAt, :latestPublishedAt
+    attr_accessor :title, :tags, :creator, :firstPublishedAt, :latestPublishedAt, :collectionName
   end
 
   def self.getPostIDFromPostURLString(postURLString)
@@ -68,6 +68,13 @@ class Post
       postInfo.creator = content&.dig(creatorRef, "name")
     end
 
+    colletionRef = content&.dig("Post:#{postID}", "collection", "__ref")
+    if !colletionRef.nil?
+      postInfo.collectionName = content&.dig(colletionRef, "name")
+    end
+
+   
+
     firstPublishedAt = content&.dig("Post:#{postID}", "firstPublishedAt")
     if !firstPublishedAt.nil?
       postInfo.firstPublishedAt = Time.at(0, firstPublishedAt, :millisecond) 

data/lib/ZMediumFetcher.rb

@@ -26,6 +26,7 @@ require "PathPolicy"
 require "Request"
 require "Post"
 require "User"
+require 'date'
 
 class ZMediumFetcher
 
@@ -204,7 +205,7 @@ class ZMediumFetcher
 
         postPathPolicy = PathPolicy.new(pathPolicy.getAbsolutePath(nil), "posts")
 
-        imagePathPolicy = PathPolicy.new(postPathPolicy.getAbsolutePath(nil), "images")
+        imagePathPolicy = PathPolicy.new(postPathPolicy.getAbsolutePath(nil), "assets")
         startParser = buildParser(imagePathPolicy)
 
         progress.totalPostParagraphsLength = paragraphs.length
@@ -212,7 +213,9 @@ class ZMediumFetcher
         progress.message = "Converting Post..."
         progress.printLog()
 
-        absolutePath = postPathPolicy.getAbsolutePath("#{postPath}.md")
+        postWithDatePath = "#{postInfo.firstPublishedAt.strftime("%Y-%m-%d")}-#{postPath}"
+
+        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) >= postInfo.latestPublishedAt
@@ -228,8 +231,11 @@ 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?

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ZMediumToMarkdown
 version: !ruby/object:Gem::Version
-  version: 1.6.0
+  version: 1.6.3
 platform: ruby
 authors:
 - ZhgChgLi
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-06-06 00:00:00.000000000 Z
+date: 2022-06-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri