87 lines
2.2 KiB
Python
87 lines
2.2 KiB
Python
from lxml import etree
|
|
import re
|
|
|
|
W_TAGS = ['w']
|
|
C_TAGS = ['c']
|
|
S_TAGS = ['S', 'pc']
|
|
|
|
# reads a TEI xml file and returns a dictionary:
|
|
# { <sentence_id>: {
|
|
# sid: <sentence_id>, # serves as index in MongoDB
|
|
# text: ,
|
|
# tokens: ,
|
|
# }}
|
|
def parse_tei(filepath):
|
|
guess_corpus = None # SSJ | KRES
|
|
res_dict = {}
|
|
with open(filepath, "r") as fp:
|
|
# remove namespaces
|
|
xmlstr = fp.read()
|
|
xmlstr = re.sub('\\sxmlns="[^"]+"', '', xmlstr, count=1)
|
|
xmlstr = re.sub(' xml:', ' ', xmlstr)
|
|
|
|
root = etree.XML(xmlstr.encode("utf-8"))
|
|
|
|
divs = [] # in ssj, there are divs, in Kres, there are separate files
|
|
if "id" in root.keys():
|
|
# Kres files start with <TEI id=...>
|
|
guess_corpus = "KRES"
|
|
divs = [root]
|
|
else:
|
|
guess_corpus = "SSJ"
|
|
divs = root.findall(".//div")
|
|
|
|
# parse divs
|
|
for div in divs:
|
|
f_id = div.get("id")
|
|
|
|
# parse paragraphs
|
|
for p in div.findall(".//p"):
|
|
p_id = p.get("id").split(".")[-1]
|
|
|
|
# parse sentences
|
|
for s in p.findall(".//s"):
|
|
s_id = s.get("id").split(".")[-1]
|
|
sentence_text = ""
|
|
sentence_tokens = []
|
|
|
|
# parse tokens
|
|
for el in s.iter():
|
|
if el.tag in W_TAGS:
|
|
el_id = el.get("id").split(".")[-1]
|
|
if el_id[0] == 't':
|
|
el_id = el_id[1:] # ssj W_TAG ids start with t
|
|
sentence_text += el.text
|
|
sentence_tokens += [(
|
|
"w",
|
|
el_id,
|
|
el.text,
|
|
el.get("lemma"),
|
|
(el.get("msd") if guess_corpus == "KRES" else el.get("ana").split(":")[-1]),
|
|
)]
|
|
elif el.tag in C_TAGS:
|
|
el_id = el.get("id") or "none" # only Kres' C_TAGS have ids
|
|
el_id = el_id.split(".")[-1]
|
|
sentence_text += el.text
|
|
sentence_tokens += [("c", el_id, el.text,)]
|
|
elif el.tag in S_TAGS:
|
|
sentence_text += " " # Kres' <S /> doesn't contain .text
|
|
else:
|
|
# pass links and linkGroups
|
|
# print(el.tag)
|
|
pass
|
|
sentence_id = "{}.{}.{}".format(f_id, p_id, s_id)
|
|
"""
|
|
print(sentence_id)
|
|
print(sentence_text)
|
|
print(sentence_tokens)
|
|
"""
|
|
if sentence_id in res_dict:
|
|
raise KeyError("duplicated id: {}".format(sentence_id))
|
|
res_dict[sentence_id] = {
|
|
"sid": sentence_id,
|
|
"text": sentence_text,
|
|
"tokens": sentence_tokens
|
|
}
|
|
return res_dict
|