Skip to content
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

Jump to bottom

Issue 85 #86

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Issue 85 #86

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b27b445
improving code for block ud.pt.AddMwt
arademaker Apr 16, 2021
f56f37b
improving the handling of relations
arademaker Apr 16, 2021
60a9f82
more contractions from PT
arademaker Apr 16, 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
53 changes: 50 additions & 3 deletions udapi/block/ud/pt/addmwt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,13 +18,19 @@
'dessa': {'form': 'de essa', 'lemma': 'de esse'},
'dessas': {'form': 'de essas', 'lemma': 'de esse'},
'desse': {'form': 'de esse', 'lemma': 'de esse'},
'comigo': {'form': 'com mim', 'lemma': 'com mim',
'upos': 'ADP PRON', 'main': 1, 'shape': 'subtree'},
'conosco': {'form': 'com nós', 'lemma': 'com nós',
'upos': 'ADP PRON', 'main': 1, 'shape': 'subtree'},
'desses': {'form': 'de esses', 'lemma': 'de esse'},
'desta': {'form': 'de esta', 'lemma': 'de este'},
'destas': {'form': 'de estas', 'lemma': 'de este'},
'deste': {'form': 'de este', 'lemma': 'de este'},
'destes': {'form': 'de estes', 'lemma': 'de este'},
'disso': {'form': 'de isso', 'lemma': 'de este'},
'disto': {'form': 'de isto', 'lemma': 'de este'},
'disso': {'form': 'de isso', 'lemma': 'de isso',
'upos': 'ADP PRON', 'main': 1, 'shape': 'subtree', 'deprel': 'case *'},
'disto': {'form': 'de isto', 'lemma': 'de isto',
'upos': 'ADP PRON', 'main': 1, 'shape': 'subtree'},
'do': {'form': 'de o', 'lemma': 'de o'}, # 'upos': 'ADP PRON', 'deprel': 'case *''
'dos': {'form': 'de os', 'lemma': 'de o'},
'dum': {'form': 'de um', 'lemma': 'de um'},
Expand All @@ -36,9 +42,40 @@
'nesses': {'form': 'em esses', 'lemma': 'em esse'},
'nesta': {'form': 'em esta', 'lemma': 'em este'},
'neste': {'form': 'em este', 'lemma': 'em este'},

'nele': {'form': 'em ele', 'lemma': 'em ele',
'upos': 'ADP PRON', 'main': 1, 'shape': 'subtree', 'deprel': 'case *'},

'naquilo': {'form': 'em aquilo', 'lemma': 'em aquilo',
'upos': 'ADP PRON', 'main': 1, 'shape': 'subtree', 'deprel': 'case *',
'feats': '_ Gender=Masc|Number=Sing|PronType=Dem'},

'àquela': {'form': 'a aquela', 'lemma': 'a aquilo',
'upos': 'ADP PRON', 'main': 1, 'shape': 'subtree', 'deprel': 'case *',
'feats': '_ Gender=Fem|Number=Sing|PronType=Dem'},

# aquele can be `det` or `pron`
'naquele': {'form': 'em aquele', 'lemma': 'em aquele',
'upos': 'ADP PRON', 'main': 1, 'shape': 'subtree', 'deprel': 'case *',
'feats': '_ Gender=Masc|Number=Sing|PronType=Dem'},
'naquela': {'form': 'em aquela', 'lemma': 'em aquele',
'upos': 'ADP PRON', 'main': 1, 'shape': 'subtree', 'deprel': 'case *',
'feats': '_ Gender=Fem|Number=Sing|PronType=Dem'},
'naqueles': {'form': 'em aqueles', 'lemma': 'em aquele',
'upos': 'ADP PRON', 'main': 1, 'shape': 'subtree', 'deprel': 'case *',
'feats': '_ Gender=Masc|Number=Plur|PronType=Dem'},
'naquelas': {'form': 'em aquelas', 'lemma': 'em aquele',
'upos': 'ADP PRON', 'main': 1, 'shape': 'subtree', 'deprel': 'case *',
'feats': '_ Gender=Fem|Number=Plur|PronType=Dem'},

'daquele': {'form': 'de aquele', 'lemma': 'de aquele',
'upos': 'ADP PRON', 'main': 1, 'shape': 'subtree', 'deprel': 'case *',
'feats': '_ Gender=Masc|Number=Plur|PronType=Dem'},

'nisso': {'form': 'em isso', 'lemma': 'em este'},
'nisto': {'form': 'em isto', 'lemma': 'em este',
'upos': 'ADP PRON', 'main': 1, 'shape': 'subtree'},

'no': {'form': 'em o', 'lemma': 'em o'}, # PRON cases are excluded below
'nos': {'form': 'em os', 'lemma': 'em o'}, # PRON cases are excluded below
'num': {'form': 'em um', 'lemma': 'em um'},
Expand Down Expand Up @@ -66,10 +103,20 @@
for pronoun in 'ela ele eles elas'.split():
MWTS['d' + pronoun] = {
'form': 'de ' + pronoun,
'lemma': 'de ' + pronoun,
'lemma': 'de ele',
'upos': 'ADP PRON',
'deprel': 'case *',
'main': 1,
'shape': 'subtree',
}
for pronoun in 'ela ele eles elas'.split():
MWTS['n' + pronoun] = {
'form': 'em ' + pronoun,
'lemma': 'em ele',
'upos': 'ADP PRON',
'deprel': 'case *',
'main': 1,
'feats': '_ *',
'shape': 'subtree',
}

Expand Down