Move summary & page parsing code to lib/parse/

1 files changed, 112 insertions, 0 deletions

diff --git a/lib/parse/summary.js b/lib/parse/summary.js
new file mode 100644
index 0000000..8787554
--- /dev/null
+++ b/lib/parse/summary.js
@@ -0,0 +1,112 @@
+var _ = require('lodash');
+var marked = require('marked');
+
+
+// Utility function for splitting a list into groups
+function splitBy(list, starter, ender) {
+    var starts = 0;
+    var ends = 0;
+    var group = [];
+
+    // Groups
+    return _.reduce(list, function(groups, value) {
+        // Ignore start and end delimiters in resulted groups
+        if(starter(value)) {
+            starts++;
+        } else if(ender(value)) {
+            ends++;
+        }
+
+        // Add current value to group
+        group.push(value);
+
+        // We've got a matching
+        if(starts === ends && starts !== 0) {
+            // Add group to end groups
+            // (remove starter and ender token)
+            groups.push(group.slice(1, -1));
+
+            // Reset group
+            group = [];
+        }
+
+        return groups;
+    }, []);
+}
+
+function listSplit(nodes, start_type, end_type) {
+    return splitBy(nodes, function(el) {
+        return el.type === start_type;
+    }, function(el) {
+        return el.type === end_type;
+    });
+}
+
+// Get the biggest list
+// out of a list of marked nodes
+function filterList(nodes) {
+    return _.chain(nodes)
+    .toArray()
+    .rest(function(el) {
+        // Get everything after list_start
+        return el.type !== 'list_start';
+    })
+    .reverse()
+    .rest(function(el) {
+        // Get everything after list_end (remember we're reversed)
+        return el.type !== 'list_end';
+    })
+    .reverse()
+    .value().slice(1, -1);
+}
+
+// Parses an Article or Chapter title
+// supports extracting links
+function parseTitle(src) {
+    // Check if it's a link
+    var matches = marked.InlineLexer.rules.link.exec(src);
+
+    // Not a link, return plain text
+    if(!matches) {
+        return {
+            title: src,
+            path: null,
+        };
+    }
+
+    return {
+        title: matches[1],
+        path: matches[2],
+    };
+}
+
+function parseArticle(nodes) {
+    return parseTitle(_.first(nodes).text);
+}
+
+function parseChapter(nodes) {
+    return {
+        chapter: parseTitle(_.first(nodes).text),
+        articles: _.map(listSplit(filterList(nodes), 'list_item_start', 'list_item_end'), parseArticle)
+    };
+}
+
+function parseSummary(src) {
+    var nodes = marked.lexer(src);
+
+    // Get out list of chapters
+    var chapterList = filterList(nodes);
+
+    // Split out chapter sections
+    var chapters = _.chain(listSplit(chapterList, 'list_item_start', 'list_item_end'))
+    .map(parseChapter)
+    .value();
+
+    return {
+        chapters: chapters
+    };
+}
+
+
+// Exports
+module.exports = parseSummary;