The first working version of generate_html.py

1 files changed, 104 insertions, 0 deletions

diff --git a/generate_html.py b/generate_html.py
new file mode 100644
index 0000000..ab968e8
--- /dev/null
+++ b/generate_html.py
@@ -0,0 +1,104 @@
+#!/usr/bin/python
+import re
+import codecs
+from xml.etree import ElementTree as et
+import logging
+#logging.basicConfig(level=logging.DEBUG)
+
+cur_year = 2012
+
+
+def csv2dict(filename):
+    out_dict = {}
+    splitRE = re.compile(r'\s+')
+    field_names = ['no', 'test', 'cs_abbr', 'cs_name',
+            'de_abbr', 'de_name']
+    with codecs.open(filename, 'rb', 'utf8') as csvfile:
+        for row in csvfile:
+            line_dict = dict(zip(field_names, splitRE.split(row)))
+            out_dict[line_dict['cs_abbr']] = line_dict
+    return out_dict
+
+
+def parse_body(elem):
+    out = []
+    body = et.Element("p")
+    logging.debug("body elem = %s", elem)
+    verses = list(elem.getiterator("L"))
+    logging.debug("verses = %s", verses)
+    logging.debug("verses = len %s", len(verses))
+    if len(verses) > 0:
+        body.text = verses[0].text
+        logging.debug("first line = %s", body.text)
+        if len(verses) > 1:
+            for line in verses[1:]:
+                l = et.SubElement(body, "br")
+                logging.debug("another line = %s", line.text)
+                l.tail = line.text
+    ref = elem.find("SL")
+    logging.debug("ref = %s", ref)
+    logging.debug("ref = len %s", len(ref))
+    out.append(body)
+    if ref is not None:
+        sig = et.Element("p")
+        sig.attrib['class'] = "reference"
+        sig.text = ref.text
+        out.append(sig)
+    return out
+
+
+def parse_one(elem):
+    logging.debug("losung = %s", elem)
+    out = et.Element("article", attrib={
+        "id": "%4d-%02d-%02d" % (cur_year, int(elem.attrib["m"]),
+            int(elem.attrib["d"]))
+        })
+    head = et.SubElement(out, "header")
+    title = et.SubElement(head, "h1")
+    title.text = elem.find("TL").text
+    for tst in ['OT', 'NT']:
+        sect = elem.find(tst)
+        for el in parse_body(sect):
+            out.append(el)
+    return out
+
+
+def parse_file(filename):
+    tree = et.parse(filename).getroot()
+    doc = et.Element("html")
+    head = et.SubElement(doc, "head")
+    et.SubElement(head, "meta", attrib={"charset": "utf-8"})
+    et.SubElement(head, "meta", attrib={
+        "name": "viewport",
+        "content": "width=device-width, initial-scale=1.0, " + \
+                " maximum-scale=2.0, user-scalable=yes"})
+    style = et.SubElement(head, "style")
+    style.text = """
+        body {
+            font-size: 120%;
+        }
+        h1 {
+            font-size: 1em;
+        }
+        article {
+            display: none;
+        }
+        .reference {
+            text-align: right;
+        }
+    """
+    et.SubElement(head, "script",
+            attrib={
+                "type": "text/javascript",
+                "src": "hesla.js"
+            })
+    title = et.SubElement(head, "title")
+    title.text = "Title"
+    body = et.SubElement(doc, "body")
+    for los in tree.getiterator("LOSUNG"):
+        body.append(parse_one(los))
+
+    return et.tostring(doc, encoding="utf-8")
+
+if __name__ == "__main__":
+    print(parse_file("hes12-01.xml"))