#!/usr/bin/python3
import codecs
import logging
import re
import sys
import jinja2
import xml.etree.ElementTree as et
logging.basicConfig(
format="%(levelname)s:%(funcName)s:%(message)s", level=logging.INFO
)
cur_year = 2023
book_abbrs = {
"Gn": "Gen",
"Ex": "Exod",
"Lv": "Lev", # NA in source code,
"Nu": "Num",
"Dt": "Deut",
"Jos": "Josh",
"Jdc": "Judg",
"Rth": "Ruth",
"1Sm": "1%20Sam",
"2Sm": "2%20Sam",
"1Rg": "1%20Kgs",
"2Rg": "2%20Kgs",
"1Chr": "1%20Chr",
"2Chr": "2%20Chr",
"Esr": "Ezra",
"Neh": "Neh",
"Esth": "Esth", # NA in source code,
"Job": "Job",
"Ps": "Ps",
"Prv": "Prov",
"Eccl": "Eccl",
"Song": "Song", # NA in source code,
"Is": "Isa",
"Jr": "Jer",
"Thr": "Lam",
"Ez": "Ezek",
"Dn": "Dan",
"Hos": "Hos",
"Joel": "Joel",
"Am": "Amos",
"Obad": "Obad", # NA in source code
"Jon": "Jonah",
"Mch": "Mic",
"Nah": "Nah", # NA in source code
"Hab": "Hab",
"Zph": "Zeph",
"Hgg": "Hag",
"Zch": "Zech",
"Ml": "Mal",
"Mt": "Matt",
"Mc": "Mark",
"L": "Luke",
"J": "John",
"Act": "Acts",
"R": "Rom",
"1K": "1%20Cor",
"2K": "2%20Cor",
"G": "Gal",
"E": "Eph",
"Ph": "Phil",
"Kol": "Col",
"1Th": "1%20Thess",
"2Th": "2%20Thess",
"1T": "1%20Tim",
"2T": "2%20Tim",
"Tt": "Titus",
"Phm": "Phlm",
"H": "Heb",
"Jc": "Jas",
"1P": "1%20Pet",
"2P": "2%20Pet",
"1J": "1%20John",
"2J": "2%20John",
"3J": "3%20John",
"Jd": "Jude",
"Ap": "Rev",
}
def csv2dict(filename):
out_dict = {}
split_re = 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, split_re.split(row)))
out_dict[line_dict["cs_abbr"]] = line_dict
logging.debug("out_dict:\n%s", out_dict)
return out_dict
def parse_verses(lines):
"""
Having list of <L> elements, make the text out of them (with
<BR> elements where necessary).
"""
out = ""
logging.debug("lines = %s", ",".join(
[et.tostring(l, encoding='unicode') for l in lines]))
logging.debug("lines = len %s", len(lines))
if len(lines) > 0:
out = lines[0].text
if len(lines) > 1:
for line in lines[1:]:
logging.debug("lines = %s", lines)
logging.debug("another line = %s", line.text)
if line.text is not None:
out += "<br>\n" + line.text
logging.debug("body = %s", out)
return out
def parse_body(elem):
"""Parse one verse element
Example could be (or NT instead of OT, or DAY):
<OT>
<S b="Ps" ch="91" v="9"/>
<L>V Hospodinu je tvé útočiště.</L>
<SL>Žalm 91,9</SL>
</OT>
"""
logging.debug('elem:%s', et.tostring(elem, encoding='unicode'))
if len(list(elem)) == 0:
return None
wword = {"text": ""}
source_elem = elem.find("S")
logging.debug("S elem = %s", et.tostring(source_elem, encoding='unicode'))
logging.debug("S elem = attrib %s", source_elem.attrib)
# biblical reference (computer readable)
wword["ref_id"] = {
"book": source_elem.attrib["b"],
"chapter": source_elem.attrib["ch"],
"verse": source_elem.attrib["v"],
}
logging.debug("wword['ref_id'] = %s", wword["ref_id"])
# biblical reference (compatible with the English Bible programs)
try:
wword["int_ref_id"] = wword["ref_id"].copy()
wword["int_ref_id"]["book"] = book_abbrs[wword["ref_id"]["book"]]
logging.debug("book = %s / %s", wword["ref_id"], wword["int_ref_id"])
except KeyError:
logging.error("book = %s", wword["ref_id"])
raise
# text of the verse
wword["text"] = parse_verses(list(elem.iter("L")))
# references
ref = elem.find("SL")
logging.debug("ref = %s", et.tostring(ref, encoding='unicode'))
if ref is not None:
logging.debug("ref.text = %s", ref.text)
wword["ref"] = ref.text
return wword
def parse_losung(elem):
"""
Parse one losung. Example:
<LOSUNG d="1" m="1">
<TL>Pátek 1. ledna 2021</TL>
<OT>
<S b="Lv" ch="19" v="11"/>
<L>Nebudete krást ani obelhávat a podvádět svého bližního.</L>
<SL>3.Mojžíšova 19,11</SL>
</OT>
<NT>
<S b="1P" ch="3" v="8"/>
<L>Všichni buďte jedné mysli, soucitní, plní bratrské lásky,
milosrdní a pokorní, neodplácejte zlým za zlé ani urážkou za
urážku, naopak žehnejte; vždyť jste byli povoláni k tomu, abyste
se stali dědici požehnání.</L>
<SL>1.Petrova 3,8-9</SL>
</NT>
<Ev><SL>Lukáš 4,16-21</SL></Ev>
<Ep><SL>Jakubova 4,13-15</SL></Ep>
<Pr><SL>Filipským 4,10-20</SL></Pr>
<AT><SL>Jozue 1,1-9</SL></AT>
<Bl><SL>Žalm 100</SL></Bl>
</LOSUNG>
<LOSUNG d="2" m="1">
<TL>Sobota 2. ledna 2021</TL>
<OT>
<S b="Neh" ch="8" v="8"/>
<L>Četli z knihy Božího zákona po oddílech a vykládali smysl, aby
lid rozuměl tomu, co četli.</L>
<SL>Nehemiáš 8,8</SL>
</OT>
<NT>
<S b="Act" ch="28" v="30"/>
<L>Pavel zůstal celé dva roky v najatém bytě a přijímal všechny,
kdo za ním přišli, zvěstoval Boží království a učil všemu o Pánu
Ježíši Kristu bez bázně a bez překážek.</L>
<SL>Skutky 28,30-31</SL>
</NT>
<SR><SL>Jozue 24,1-26</SL></SR>
<CR><SL>Lukáš 3,1-6</SL></CR>
</LOSUNG>
"""
logging.debug("losung = %s\n", et.tostring(elem, encoding='unicode'))
out = {}
date_id = (
cur_year,
int(elem.attrib["m"]),
int(elem.attrib["d"]),
)
out["date_id"] = "%4d-%02d-%02d" % (date_id)
logging.debug("date_id = %s", out["date_id"])
out["date_full"] = elem.find("TL").text
out["watchwords"] = []
for tst in ["OT", "NT"]:
sect = elem.find(tst)
out["watchwords"].append(parse_body(sect))
out["readings"] = []
for read in ["SR", "CR", "Ev", "Ep", "Pr", "AT", "Bl"]:
sect = elem.find(read)
if sect is not None:
try:
out["readings"].append(
"\n".join([el.text for el in sect.findall("SL")])
)
except AttributeError:
logging.exception("Parsing heslo pro %s", sect)
logging.debug("readings = %s", out['readings'])
out["chronicles"] = []
for chron in elem.findall("C"):
out["chronicles"].append(
"\n".join([line.text for line in chron.findall("L")])
)
return date_id, out
def parse_day(elem, whole_dict):
"""
Parsse <DAY> element.
Example:
<DAY d="1" m="1" type="holiday" name="Nový Rok ">
<S b="Kol" ch="3" v="17"/>
<L>Všechno, cokoli mluvíte nebo děláte,</L>
<L>čiňte ve jménu Pána Ježíše a skrze něho děkujte Bohu Otci.</L>
<SL>Koloským 3,17</SL>
</DAY>
<DAY d="17" m="2" type="sunday" name="Invocavit"
meaning="Vzývati mne bude a vyslyším jej. Žalm 91,15" ord="7">
<S b="1J" ch="3" v="8"/>
<L>Proto se zjevil Syn Boží, aby zmařil činy ďáblovy.</L>
<SL>1.Janova 3,8b</SL>
</DAY>
<DAY d="13" m="1" type="week" name="Alianční modlitební týden ">
</DAY>
"""
date_id = (
cur_year,
int(elem.attrib["m"]),
int(elem.attrib["d"]),
)
logging.debug("date_id = %s", date_id)
out = whole_dict[date_id]
if elem.attrib["type"] == "holiday":
out["holy_name"] = elem.attrib["name"].strip()
out["holy_text"] = parse_body(elem)
elif elem.attrib["type"] == "sunday":
out["sun_name"] = elem.attrib["name"].strip()
if "meaning" in elem.attrib:
out["sun_mean"] = elem.attrib["meaning"].strip()
out["sun_ord"] = int(elem.attrib["ord"])
out["sun_text"] = parse_body(elem)
elif elem.attrib["type"] == "week":
out["week_title"] = elem.attrib["name"].strip()
else:
raise ValueError("Unknown DAY type = %s", elem.attrib["type"])
def parse_file(filename):
tree = et.parse(filename).getroot()
article_dict = {}
env = jinja2.Environment(loader=jinja2.FileSystemLoader("templates"))
template = env.get_template("czech.html")
for los in tree.iter("LOSUNG"):
key, text = parse_losung(los)
article_dict[key] = text
for los in tree.iter("DAY"):
parse_day(los, article_dict)
article_list = []
for key in sorted(article_dict.keys()):
article_list.append(article_dict[key])
return template.render(articles=article_list)
if __name__ == "__main__":
print(parse_file(sys.argv[1]))
