restructure and tests

squash! restructure and tests

3 files changed, 77 insertions, 57 deletions

diff --git a/src/services/html_converter/html_line_converter.service.js b/src/services/html_converter/html_line_converter.service.js
index d8f5ecb8..e448d5cd 100644
--- a/src/services/html_converter/html_line_converter.service.js
+++ b/src/services/html_converter/html_line_converter.service.js
@@ -1,3 +1,5 @@
+import { getTagName } from './utility.service.js'
+
 /**
  * This is a tiny purpose-built HTML parser/processor. This basically detects
  * any type of visual newline and converts entire HTML into a array structure.
@@ -26,12 +28,6 @@ export const convertHtmlToLines = (html) => {
   let textBuffer = '' // Current line content
   let tagBuffer = null // Current tag buffer, if null = we are not currently reading a tag
 
-  // Extracts tag name from tag, i.e. <span a="b"> => span
-  const getTagName = (tag) => {
-    const result = /(?:<\/(\w+)>|<(\w+)\s?[^/]*?\/?>)/gi.exec(tag)
-    return result && (result[1] || result[2])
-  }
-
   const flush = () => { // Processes current line buffer, adds it to output buffer and clears line buffer
     if (textBuffer.trim().length > 0 && !level.some(l => ignoredTags.has(l))) {
       buffer.push({ text: textBuffer })
diff --git a/src/services/html_converter/html_tree_converter.service.js b/src/services/html_converter/html_tree_converter.service.js
index badd473a..804d35d7 100644
--- a/src/services/html_converter/html_tree_converter.service.js
+++ b/src/services/html_converter/html_tree_converter.service.js
@@ -1,3 +1,5 @@
+import { getTagName } from './utility.service.js'
+
 /**
  * This is a not-so-tiny purpose-built HTML parser/processor. This parses html
  * and converts it into a tree structure representing tag openers/closers and
@@ -93,54 +95,3 @@ export const convertHtmlToTree = (html) => {
   flushText()
   return buffer
 }
-
-// Extracts tag name from tag, i.e. <span a="b"> => span
-export const getTagName = (tag) => {
-  const result = /(?:<\/(\w+)>|<(\w+)\s?.*?\/?>)/gi.exec(tag)
-  return result && (result[1] || result[2])
-}
-
-export const processTextForEmoji = (text, emojis, processor) => {
-  const buffer = []
-  let textBuffer = ''
-  for (let i = 0; i < text.length; i++) {
-    const char = text[i]
-    if (char === ':') {
-      const next = text.slice(i + 1)
-      let found = false
-      for (let emoji of emojis) {
-        if (next.slice(0, emoji.shortcode.length + 1) === (emoji.shortcode + ':')) {
-          found = emoji
-          break
-        }
-      }
-      if (found) {
-        buffer.push(textBuffer)
-        textBuffer = ''
-        buffer.push(processor(found))
-        i += found.shortcode.length + 1
-      } else {
-        textBuffer += char
-      }
-    } else {
-      textBuffer += char
-    }
-  }
-  if (textBuffer) buffer.push(textBuffer)
-  return buffer
-}
-
-export const getAttrs = tag => {
-  const innertag = tag
-    .substring(1, tag.length - 1)
-    .replace(new RegExp('^' + getTagName(tag)), '')
-    .replace(/\/?$/, '')
-    .trim()
-  const attrs = Array.from(innertag.matchAll(/([a-z0-9-]+)(?:=("[^"]+?"|'[^']+?'))?/gi))
-    .map(([trash, key, value]) => [key, value])
-    .map(([k, v]) => {
-      if (!v) return [k, true]
-      return [k, v.substring(1, v.length - 1)]
-    })
-  return Object.fromEntries(attrs)
-}
diff --git a/src/services/html_converter/utility.service.js b/src/services/html_converter/utility.service.js
new file mode 100644
index 00000000..4d0c36c2
--- /dev/null
+++ b/src/services/html_converter/utility.service.js
@@ -0,0 +1,73 @@
+/**
+ * Extract tag name from tag opener/closer.
+ *
+ * @param {String} tag - tag string, i.e. '<a href="...">'
+ * @return {String} - tagname, i.e. "div"
+ */
+export const getTagName = (tag) => {
+  const result = /(?:<\/(\w+)>|<(\w+)\s?.*?\/?>)/gi.exec(tag)
+  return result && (result[1] || result[2])
+}
+
+/**
+ * Extract attributes from tag opener.
+ *
+ * @param {String} tag - tag string, i.e. '<a href="...">'
+ * @return {Object} - map of attributes key = attribute name, value = attribute value
+ *   attributes without values represented as boolean true
+ */
+export const getAttrs = tag => {
+  const innertag = tag
+    .substring(1, tag.length - 1)
+    .replace(new RegExp('^' + getTagName(tag)), '')
+    .replace(/\/?$/, '')
+    .trim()
+  const attrs = Array.from(innertag.matchAll(/([a-z0-9-]+)(?:=("[^"]+?"|'[^']+?'))?/gi))
+    .map(([trash, key, value]) => [key, value])
+    .map(([k, v]) => {
+      if (!v) return [k, true]
+      return [k, v.substring(1, v.length - 1)]
+    })
+  return Object.fromEntries(attrs)
+}
+
+/**
+ * Finds shortcodes in text
+ *
+ * @param {String} text - original text to find emojis in
+ * @param {{ url: String, shortcode: Sring }[]} emoji - list of shortcodes to find
+ * @param {Function} processor - function to call on each encountered emoji,
+ *   function is passed single object containing matching emoji ({ url, shortcode })
+ *   return value will be inserted into resulting array instead of :shortcode:
+ * @return {Array} resulting array with non-emoji parts of text and whatever {processor}
+ *   returned for emoji
+ */
+export const processTextForEmoji = (text, emojis, processor) => {
+  const buffer = []
+  let textBuffer = ''
+  for (let i = 0; i < text.length; i++) {
+    const char = text[i]
+    if (char === ':') {
+      const next = text.slice(i + 1)
+      let found = false
+      for (let emoji of emojis) {
+        if (next.slice(0, emoji.shortcode.length + 1) === (emoji.shortcode + ':')) {
+          found = emoji
+          break
+        }
+      }
+      if (found) {
+        buffer.push(textBuffer)
+        textBuffer = ''
+        buffer.push(processor(found))
+        i += found.shortcode.length + 1
+      } else {
+        textBuffer += char
+      }
+    } else {
+      textBuffer += char
+    }
+  }
+  if (textBuffer) buffer.push(textBuffer)
+  return buffer
+}