mkhtml scripts

2 files changed, 42 insertions, 0 deletions

diff --git a/data/mkhtml_all.py b/data/mkhtml_all.py
new file mode 100644
index 0000000..6d9d662
--- /dev/null
+++ b/data/mkhtml_all.py
@@ -0,0 +1,21 @@
+import json
+
+f = open("words.json")
+words = json.load(f)
+f.close()
+
+html = ""
+track = ""
+
+for word in words:
+    html += "<tr>"
+    if word["track"] != track:
+        track = word["track"]
+        words_from_track = len([w for w in words if w["track"] == track])
+        html += f"<td rowspan={words_from_track}>{track}</td>"
+
+    html += f"<td>{word['word']}</td><td>{'<br/>'.join(word['lines'])}</td></tr>\n"
+
+htmlf = open("all_words.html", "w")
+htmlf.write(html)
+htmlf.close()
diff --git a/data/mkhtml_freq.py b/data/mkhtml_freq.py
new file mode 100644
index 0000000..8e7a7d9
--- /dev/null
+++ b/data/mkhtml_freq.py
@@ -0,0 +1,21 @@
+import json
+
+f = open("words.json")
+words = json.load(f)
+f.close()
+
+freqf = open("most_frequent")
+freq_words = freqf.read().splitlines()
+freqf.close()
+
+html = ""
+
+for idx, fw in enumerate(freq_words):
+    for word in words:
+        if word["word"] == fw:
+            html += f"<tr><td>{fw}</td><td>{word['track']}</td></tr>\n"
+
+
+htmlf = open("frequent_words.html", "w")
+htmlf.write(html)
+htmlf.close()