Skip to content

Commit

Permalink
Refactored Mapper, added ARPABETMapper, better data files.
Browse files Browse the repository at this point in the history
  • Loading branch information
Alberto Pettarin committed May 28, 2016
1 parent a9b1be2 commit 08cdb91
Show file tree
Hide file tree
Showing 19 changed files with 1,879 additions and 1,703 deletions.
145 changes: 77 additions & 68 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2,8 +2,8 @@

**ipapy** is a Python module to work with IPA strings.

* Version: 0.0.5
* Date: 2016-05-26
* Version: 0.0.6
* Date: 2016-05-28
* Developer: [Alberto Pettarin](http://www.albertopettarin.it/)
* License: the MIT License (MIT)
* Contact: [click here](http://www.albertopettarin.it/contact.html)
Expand Down Expand Up @@ -33,7 +33,6 @@ $ cd ipapy
###########
from ipapy import UNICODE_TO_IPA
from ipapy import is_valid_ipa
from ipapy.asciimapper import ASCIIMapper
from ipapy.ipachar import IPAConsonant
from ipapy.ipachar import IPAVowel
from ipapy.ipastring import IPAString
Expand All @@ -46,17 +45,17 @@ from ipapy.ipastring import IPAString
# Def.: an IPAChar is an IPA letter or diacritic/suprasegmental/tone mark

# create IPAChar from its Unicode representation
c1 = UNICODE_TO_IPA[u"a"] # open front unrounded vowel
c2 = UNICODE_TO_IPA[u"e"] # close-mid front unrounded vowel
c3 = UNICODE_TO_IPA[u"\u03B2"] # voiced bilabial non-sibilant-fricative consonant)
tS1 = UNICODE_TO_IPA[u"t͡ʃ"] # voiceless palato-alveolar sibilant-affricate consonant
tS2 = UNICODE_TO_IPA[u"t͜ʃ"] # voiceless palato-alveolar sibilant-affricate consonant
tS3 = UNICODE_TO_IPA[u"tʃ"] # voiceless palato-alveolar sibilant-affricate consonant
tS4 = UNICODE_TO_IPA[u"ʧ"] # voiceless palato-alveolar sibilant-affricate consonant
tS5 = UNICODE_TO_IPA[u"\u0074\u0361\u0283"] # voiceless palato-alveolar sibilant-affricate consonant
tS6 = UNICODE_TO_IPA[u"\u0074\u035C\u0283"] # voiceless palato-alveolar sibilant-affricate consonant
tS7 = UNICODE_TO_IPA[u"\u0074\u0283"] # voiceless palato-alveolar sibilant-affricate consonant
tS8 = UNICODE_TO_IPA[u"\u02A7"] # voiceless palato-alveolar sibilant-affricate consonant
c1 = UNICODE_TO_IPA[u"a"] # vowel open front unrounded
c2 = UNICODE_TO_IPA[u"e"] # vowel close-mid front unrounded
c3 = UNICODE_TO_IPA[u"\u03B2"] # consonant voiced bilabial non-sibilant-fricative
tS1 = UNICODE_TO_IPA[u"t͡ʃ"] # consonant voiceless palato-alveolar sibilant-affricate
tS2 = UNICODE_TO_IPA[u"t͜ʃ"] # consonant voiceless palato-alveolar sibilant-affricate
tS3 = UNICODE_TO_IPA[u"tʃ"] # consonant voiceless palato-alveolar sibilant-affricate
tS4 = UNICODE_TO_IPA[u"ʧ"] # consonant voiceless palato-alveolar sibilant-affricate
tS5 = UNICODE_TO_IPA[u"\u0074\u0361\u0283"] # consonant voiceless palato-alveolar sibilant-affricate
tS6 = UNICODE_TO_IPA[u"\u0074\u035C\u0283"] # consonant voiceless palato-alveolar sibilant-affricate
tS7 = UNICODE_TO_IPA[u"\u0074\u0283"] # consonant voiceless palato-alveolar sibilant-affricate
tS8 = UNICODE_TO_IPA[u"\u02A7"] # consonant voiceless palato-alveolar sibilant-affricate
c1 == c2 # False
c1 == c3 # False
c1 == tS1 # False
Expand Down Expand Up @@ -159,16 +158,16 @@ double = s_ipa + new_s_ipa # (concatenate s_ipa and new_s_ipa)
len(double) # 48

# new IPAString objects containing only...
s_ipa.consonants # "knknθld͡ʒ" (consonants)
s_ipa.vowels # "əiææɑəi" (vowels)
s_ipa.letters # "əkinækænθɑləd͡ʒi" (vowels and consonants)
s_ipa.cns_vwl # "əkinækænθɑləd͡ʒi" (vowels and consonants)
s_ipa.cns_vwl_pstr # "əˈkinækænˈθɑləd͡ʒi" ( + primary stress marks)
s_ipa.cns_vwl_pstr_long # "əˈkiːnækænˈθɑləd͡ʒi" ( + long marks)
s_ipa.cns_vwl_str # "əˈkinæˌkænˈθɑləd͡ʒi" ( + stress marks)
s_ipa.cns_vwl_str_len # "əˈkiːnæˌkænˈθɑləd͡ʒi" ( + length marks)
s_ipa.cns_vwl_str_len_wb # "əˈkiːn æˌkænˈθɑləd͡ʒi" ( + word breaks)
s_ipa.cns_vwl_str_len_wb_sb # "əˈkiːn æˌkænˈθɑ.lə.d͡ʒi" ( + syllable breaks)
print(s_ipa.consonants) # "knknθld͡ʒ" (consonants)
print(s_ipa.vowels) # "əiææɑəi" (vowels)
print(s_ipa.letters) # "əkinækænθɑləd͡ʒi" (vowels and consonants)
print(s_ipa.cns_vwl) # "əkinækænθɑləd͡ʒi" (vowels and consonants)
print(s_ipa.cns_vwl_pstr) # "əˈkinækænˈθɑləd͡ʒi" ( + primary stress marks)
print(s_ipa.cns_vwl_pstr_long) # "əˈkiːnækænˈθɑləd͡ʒi" ( + long marks)
print(s_ipa.cns_vwl_str) # "əˈkinæˌkænˈθɑləd͡ʒi" ( + stress marks)
print(s_ipa.cns_vwl_str_len) # "əˈkiːnæˌkænˈθɑləd͡ʒi" ( + length marks)
print(s_ipa.cns_vwl_str_len_wb) # "əˈkiːn æˌkænˈθɑləd͡ʒi" ( + word breaks)
print(s_ipa.cns_vwl_str_len_wb_sb) # "əˈkiːn æˌkænˈθɑ.lə.d͡ʒi" ( + syllable breaks)
cns = s_ipa.consonants # (store new IPA string)
cns == s_ipa.consonants # False (two different objects)
cns.is_equivalent(s_ipa.consonants) # True
Expand All @@ -177,27 +176,27 @@ cns.is_equivalent(s_ipa) # False
# print representation and name of all IPAChar objects in IPAString
for c in s_ipa:
print(u"%s\t%s" % (c, c.name))
# ə mid central unrounded vowel
# ˈ primary-stress suprasegmental
# k voiceless velar plosive consonant
# i close front unrounded vowel
# ː long suprasegmental
# n voiced alveolar nasal consonant
# word-break suprasegmental
# æ near-open front unrounded vowel
# ˌ secondary-stress suprasegmental
# k voiceless velar plosive consonant
# æ near-open front unrounded vowel
# n voiced alveolar nasal consonant
# ˈ primary-stress suprasegmental
# θ voiceless dental non-sibilant-fricative consonant
# ɑ open back unrounded vowel
# . syllable-break suprasegmental
# l voiced alveolar lateral-approximant consonant
# ə mid central unrounded vowel
# . syllable-break suprasegmental
# d͡ʒ voiced palato-alveolar sibilant-affricate consonant
# i close front unrounded vowel
# ə vowel mid central unrounded
# ˈ suprasegmental primary-stress
# k consonant voiceless velar plosive
# i vowel close front unrounded
# ː suprasegmental long
# n consonant voiced alveolar nasal
# suprasegmental word-break
# æ vowel near-open front unrounded
# ˌ suprasegmental secondary-stress
# k consonant voiceless velar plosive
# æ vowel near-open front unrounded
# n consonant voiced alveolar nasal
# ˈ suprasegmental primary-stress
# θ consonant voiceless dental non-sibilant-fricative
# ɑ vowel open back unrounded
# . suprasegmental syllable-break
# l consonant voiced alveolar lateral-approximant
# ə vowel mid central unrounded
# . suprasegmental syllable-break
# d͡ʒ consonant voiced palato-alveolar sibilant-affricate
# i vowel close front unrounded

# compare IPAString objects
s_ipa_d = IPAString(unicode_string=u"diff")
Expand Down Expand Up @@ -231,10 +230,16 @@ s_ipa_1.is_equivalent(u"at͡ʃeLoL", ignore=True) # False (ignore chars non IPA
########################
# CONVERSION FUNCTIONS #
########################
mapper = ASCIIMapper() # mapper to ASCII IPA (Kirshenbaum)
s_ascii_ipa = mapper.map_ipa_string(s_ipa) # u"@'ki:n#&,k&n'TA#l@#dZi"
s_ascii_uni = mapper.map_unicode_string(s_uni) # u"@'ki:n#&,k&n'TA#l@#dZi"
s_ascii_ipa == s_ascii_uni # True
from ipapy.kirshenbaummapper import KirshenbaumMapper
kmapper = KirshenbaumMapper() # mapper to Kirshenbaum ASCII IPA
s_k_ipa = kmapper.map_ipa_string(s_ipa) # u"@'ki:n#&,k&n'TA#l@#dZi"
s_k_uni = kmapper.map_unicode_string(s_uni) # u"@'ki:n#&,k&n'TA#l@#dZi"
s_k_ipa == s_k_uni # True

from ipapy.arpabetmapper import ARPABETMapper
amapper = ARPABETMapper() # mapper to ARPABET ASCII IPA (NOTE: stress marks are not supported yet)
s_a_ipa = amapper.map_unicode_string(u"pɹuːf") # error, long suprasegmental not mapped
s_a_ipa = amapper.map_unicode_string(u"pɹuːf", ignore=True) # u"pruwf"
```

### As A Command Line Tool
Expand All @@ -250,7 +255,8 @@ Currently, the supported operations are:
* ``chars``: list all IPA characters appearing in the IPA string
* ``check``: check if the given Unicode string is IPA valid
* ``clean``: remove characters that are not IPA valid
* ``u2a``: print the corresponding ASCII IPA (Kirshenbaum) string
* ``u2a``: print the corresponding ARPABET (ASCII IPA) string
* ``u2k``: print the corresponding Kirshenbaum (ASCII IPA) string

Run with the ``--help`` parameter to list all the available options:

Expand All @@ -263,7 +269,7 @@ usage: __main__.py [-h] [-i] [-p] [--separator [SEPARATOR]] [-s] [-u]
ipapy perform a command on the given IPA/Unicode string

positional arguments:
command [canonize|chars|check|clean|u2a]
command [canonize|chars|check|clean|u2a|u2k]
string String to canonize, check, clean, or convert

optional arguments:
Expand All @@ -290,24 +296,24 @@ $ python -m ipapy canonize "eʧiu" --separator " "
e t͡ʃ i u

$ python -m ipapy chars "eʧiu"
'e' close-mid front unrounded vowel (U+0065)
't͡ʃ' voiceless palato-alveolar sibilant-affricate consonant (U+0074 U+0361 U+0283)
'i' close front unrounded vowel (U+0069)
'u' close back rounded vowel (U+0075)
'e' vowel close-mid front unrounded (U+0065)
't͡ʃ' consonant voiceless palato-alveolar sibilant-affricate (U+0074 U+0361 U+0283)
'i' vowel close front unrounded (U+0069)
'u' vowel close back rounded (U+0075)

$ python -m ipapy chars "et͡ʃiu"
'e' close-mid front unrounded vowel (U+0065)
't͡ʃ' voiceless palato-alveolar sibilant-affricate consonant (U+0074 U+0361 U+0283)
'i' close front unrounded vowel (U+0069)
'u' close back rounded vowel (U+0075)
'e' vowel close-mid front unrounded (U+0065)
't͡ʃ' consonant voiceless palato-alveolar sibilant-affricate (U+0074 U+0361 U+0283)
'i' vowel close front unrounded (U+0069)
'u' vowel close back rounded (U+0075)

$ python -m ipapy chars "et͡ʃiu" -s
'e' close-mid front unrounded vowel (U+0065)
't' voiceless alveolar plosive consonant (U+0074)
'͡' tie-bar-above diacritic (U+0361)
'ʃ' voiceless palato-alveolar sibilant-fricative consonant (U+0283)
'i' close front unrounded vowel (U+0069)
'u' close back rounded vowel (U+0075)
'e' vowel close-mid front unrounded (U+0065)
't' consonant voiceless alveolar plosive (U+0074)
'͡' diacritic tie-bar-above (U+0361)
'ʃ' consonant voiceless palato-alveolar sibilant-fricative (U+0283)
'i' vowel close front unrounded (U+0069)
'u' vowel close back rounded (U+0075)

$ python -m ipapy check "eʧiu"
True
Expand All @@ -328,14 +334,17 @@ LLOL
$ python -m ipapy clean "/eʧiu/"
eʧiu

$ python -m ipapy u2a "eʧiu"
$ python -m ipapy u2k "eʧiu"
etSiu

$ python -m ipapy u2a "eTa"
$ python -m ipapy u2k "eTa"
The given string contains characters not IPA valid. Use the 'ignore' option to ignore them.

$ python -m ipapy u2a "eTa" -i
$ python -m ipapy u2k "eTa" -i
ea

$ python -m ipapy u2a "eʧiu" --separator " "
eh ch ih u
```
Expand Down
Loading

0 comments on commit 08cdb91

Please sign in to comment.