Created
January 24, 2014 10:53
-
-
Save andresteingress/8595350 to your computer and use it in GitHub Desktop.
my personal clj wordpress to jekyll import
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
(ns clj-wp-import.core | |
(:require [clojure.java.io :as jio] | |
[clojure.string :as str])) | |
(defn post-files | |
[f] | |
(file-seq (jio/file f))) | |
(defn remove-pre-code | |
[txt] | |
(str/replace txt #"(?s)(?i)<pre>(.+?)</pre>" "{% highlight groovy %} $1 {% endhighlight %}")) | |
(defn remove-code-language | |
([tag attr txt] (remove-code-language (vector "groovy") tag attr txt)) | |
([lang-coll tag attr txt] | |
(reduce #(str/replace %1 | |
(re-pattern (str "(?s)(?i)\\[" tag " " attr "=\"" %2 "\"\\](.+?)\\[/" tag "\\]")) | |
(str "{% highlight " %2 " %} $1 {% endhighlight %}")) txt lang-coll))) | |
(defn format-link-section [txt] | |
(str/replace txt | |
(re-pattern "(\\[\\d{1,2}\\] <a.*)") | |
(str "<div>$1</div>"))) | |
(defn format-first-link-of-link-section [txt] | |
(str/replace txt | |
(re-pattern "(<div>\\[0\\] <a.*)") | |
(str "<br><br>$1"))) | |
(defn remove-double-curly-braces [txt] | |
(str/replace (str/replace txt "{{" "") "}}" "")) | |
(defn replace-html-entites [txt] | |
(let [entities [[""" "\""] ["<" "<"] [">" ">"]]] | |
(reduce #(str/replace %1 (nth %2 0) (nth %2 1)) txt entities))) | |
(defn replace-html-entites-in-highlight [txt] | |
(reduce #(str/replace %1 (first %2) (replace-html-entites (first %2))) txt (re-seq (re-pattern "(?s)\\{% highlight (.*?) %\\} (.*?) \\{% endhighlight %\\}") txt))) | |
(defn process-post-file [file] | |
(let [s (slurp file)] | |
(->> (remove-pre-code s) | |
(remove-code-language ["groovy", "xml", "java", "scala", "kotlin"] "code" "language") | |
(remove-code-language ["groovy", "xml", "java", "scala", "kotlin"] "code" "lang") | |
(remove-code-language ["groovy", "xml", "java", "scala", "kotlin"] "sourcecode" "language") | |
(remove-code-language ["groovy", "xml", "java", "scala", "kotlin"] "sourcecode" "lang") | |
(format-link-section) | |
(format-first-link-of-link-section) | |
(remove-double-curly-braces) | |
(replace-html-entites-in-highlight) | |
))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment