From 81a7337eb3d9866f85fef30465466027b4bd7ce5 Mon Sep 17 00:00:00 2001
From: Simon Brooke <simon@journeyman.cc>
Date: Tue, 30 Apr 2019 18:35:34 +0100
Subject: [PATCH] Lots of improvements from running against real live tag soup

---
 project.clj                         |  3 +-
 src/html_to_md/html_to_md.clj       | 50 +++++++++++++++++------------
 src/html_to_md/transformer.clj      |  2 +-
 test/html_to_md/html_to_md_test.clj |  2 +-
 4 files changed, 33 insertions(+), 24 deletions(-)

diff --git a/project.clj b/project.clj
index 654fd11..4edbf3a 100644
--- a/project.clj
+++ b/project.clj
@@ -5,6 +5,7 @@
               :url "http://www.eclipse.org/legal/epl-v10.html"}
     :dependencies [[org.clojure/clojure "1.8.0"]
                    [enlive "1.1.6"]]
-    :plugins [[lein-codox "0.10.3"]]
+    :plugins [[lein-codox "0.10.3"]
+              [lein-release "1.0.5"]]
     :lein-release {:deploy-via :clojars}
     :signing {:gpg-key "Simon Brooke (Stultus in monte) <simon@journeyman.cc>"})
diff --git a/src/html_to_md/html_to_md.clj b/src/html_to_md/html_to_md.clj
index 5bc9716..662a23d 100644
--- a/src/html_to_md/html_to_md.clj
+++ b/src/html_to_md/html_to_md.clj
@@ -7,15 +7,18 @@
 (defn markdown-a
     "Process the anchor element `e` into markdown, using dispatcher `d`."
     [e d]
-    (apply
-        str
-        (flatten
-            (list
-                "["
-                (map #(process % d) (:content e))
-                "]("
-                (-> e :attrs :href)
-                ")"))))
+    (str
+        "["
+        (s/trim (apply str (process (:content e) d)))
+        "]("
+        (-> e :attrs :href)
+        ")"))
+
+(defn markdown-br
+    "Process the line-break element `e`, so beloved of tag-soupers, into
+    markdown"
+    [e d]
+    "\n\n")
 
 (defn markdown-code
     "Process the code or samp `e` into markdown, using dispatcher `d`."
@@ -51,15 +54,12 @@
     "Process the header element `e` into markdown, with level `level`,
     using dispatcher `d`."
     [e d level]
-    (apply
-        str
-        (flatten
-            (list
-                "\n"
-            (take level (repeat "#"))
-                " "
-            (map #(process % d) (:content e))
-                "\n"))))
+    (str
+        "\n"
+        (apply str (take level (repeat "#")))
+        " "
+        (s/trim (apply str (process (:content e) d)))
+        "\n"))
 
 (defn markdown-h1
     "Process the header element `e` into markdown, with level 1, using
@@ -105,7 +105,7 @@
 (defn markdown-img
     "Process this image element `e` into markdown, using dispatcher `d`."
     [e d]
-    (str "![" (-> e :attrs :alt) "](" (-> e :attrs :src) ")"))
+    (str "![image: " (-> e :attrs :alt) "](" (-> e :attrs :src) ")"))
 
 (defn markdown-ol
     "Process this ordered list element `e` into markdown, using dispatcher
@@ -120,10 +120,15 @@
                             str
                             (flatten
                                 (list "\n" (inc %2) ". " (process %1 d))))
-                       (:content e)
+                       (html/select e [:li])
                        (range))))
         "\n\n"))
 
+(defn markdown-omit
+    "Don't process the element `e` into markdown, but return `nil`."
+    [e d]
+    nil)
+
 (defn markdown-pre
     "Process the preformatted emphasis element `e` into markdown, using
     dispatcher `d`."
@@ -155,13 +160,14 @@
                             str
                             (flatten
                                 (list "\n* " (process % d))))
-                       (:content e))))
+                       (html/select e [:li]))))
         "\n\n"))
 
 
 (def markdown-dispatcher
     {:a markdown-a
      :b markdown-strong
+     :br markdown-br
      :code markdown-code
      :body markdown-default
      :div markdown-div
@@ -179,8 +185,10 @@
      :p markdown-div
      :pre markdown-pre
      :samp markdown-code
+     :script markdown-omit
      :span markdown-default
      :strong markdown-strong
+     :style markdown-omit
      :ul markdown-ul
      })
 
diff --git a/src/html_to_md/transformer.clj b/src/html_to_md/transformer.clj
index b08ef9d..931343c 100644
--- a/src/html_to_md/transformer.clj
+++ b/src/html_to_md/transformer.clj
@@ -29,7 +29,7 @@
 
         (string? element) element
         (or (seq? element) (vector? element))
-        (map #(process % dispatcher) element)))
+        (doall (map #(process % dispatcher) element))))
 
 (defn- transformer-dispatch
     [a _]
diff --git a/test/html_to_md/html_to_md_test.clj b/test/html_to_md/html_to_md_test.clj
index 0778ec7..b328976 100644
--- a/test/html_to_md/html_to_md_test.clj
+++ b/test/html_to_md/html_to_md_test.clj
@@ -73,7 +73,7 @@
 
 (deftest img-test
     (testing "Image tag."
-        (let [expected "![Hello dere!](http://foo.bar/image.png)"
+        (let [expected "![image: Hello dere!](http://foo.bar/image.png)"
               actual (process
                          {:tag :img
                           :attrs {:src "http://foo.bar/image.png"