Skip to content

Fix issue #552 by removing the unreachable branch #563

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
bact merged 3 commits into from
May 20, 2021
Merged

Fix issue #552 by removing the unreachable branch #563

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d049262
Fix issue #552 by removing the unreachable branch
May 18, 2021
e346591
Reorder condition in ifs, make it more consistent
bact May 20, 2021
40671c3
Reformatting + docstring
bact May 20, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
47 changes: 20 additions & 27 deletions pythainlp/transliterate/royin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -152,10 +152,11 @@ def _replace_consonants(word: str, consonants: str) -> str:

if len(consonants) == 1:
return word.replace(consonants[0], _CONSONANTS[consonants[0]][0])
len_cons = len(consonants)

i = 0
len_cons = len(consonants)
while i < len_cons:
len_word = len(word)
if i == 0:
if consonants[0] == _HO_HIP:
word = word.replace(consonants[0], "")
Expand All @@ -166,16 +167,18 @@ def _replace_consonants(word: str, consonants: str) -> str:
consonants[0], _CONSONANTS[consonants[0]][0]
)
i += 1
elif consonants[i] == _RO_RUA and i == len(word) and word[i - 1] == _RO_RUA:
word = word.replace(
consonants[i], _CONSONANTS[consonants[i]][1]
)
elif consonants[i] == _RO_RUA and i < len(word):
if i + 1 == len(word) and word[i] == _RO_RUA:
elif (
i == len_word
and consonants[i] == _RO_RUA
and word[i - 1] == _RO_RUA
):
word = word.replace(consonants[i], _CONSONANTS[consonants[i]][1])
elif i < len_word and consonants[i] == _RO_RUA:
if i + 1 == len_word and word[i] == _RO_RUA:
word = word.replace(
consonants[i], _CONSONANTS[consonants[i]][1]
)
elif word[i] == _RO_RUA and i + 1 < len(word):
elif i + 1 < len_word and word[i] == _RO_RUA:
if word[i + 1] == _RO_RUA:
word = list(word)
del word[i + 1]
Expand All @@ -192,19 +195,12 @@ def _replace_consonants(word: str, consonants: str) -> str:
i += 1
else:
word = word.replace(
consonants[i],
_CONSONANTS[consonants[i]][1]
consonants[i], _CONSONANTS[consonants[i]][1]
)
i += 1
elif word[i] == _RO_RUA:
word = word.replace(
consonants[i], _CONSONANTS[consonants[i]][1]
)
i += 1
else:
word = word.replace(
consonants[i],
_CONSONANTS[consonants[i]][1]
consonants[i], _CONSONANTS[consonants[i]][1]
)
i += 1
else:
Expand All @@ -216,10 +212,6 @@ def _replace_consonants(word: str, consonants: str) -> str:

# support function for romanize()
def _romanize(word: str) -> str:
"""
:param str word: a Thai word, should have already been tokenized.
:return: Spells out how the Thai word should be pronounced.
"""
word = _replace_vowels(_normalize(word))
consonants = _RE_CONSONANT.findall(word)

Expand All @@ -235,13 +227,14 @@ def _romanize(word: str) -> str:


def romanize(text: str) -> str:
"""
Rendering Thai words in the Latin alphabet or "romanization",
using the Royal Thai General System of Transcription (RTGS),
which is the official system published by the Royal Institute of Thailand.
"""Render Thai words in Latin alphabet, using RTGS

Royal Thai General System of Transcription (RTGS),
is the official system by the Royal Institute of Thailand.

:param str text: Thai text to be romanized
:return: A string of Thai words rendered in the Latin alphabet.
:param text: Thai text to be romanized
:type text: str
:return: A string of Thai words rendered in the Latin alphabet
:rtype: str
"""
words = word_tokenize(text)
Expand Down