hendrik
/
patacrep
mirror of https://github.com/patacrep/patacrep.git
1
0
Fork 0
Code Issues Releases Wiki Activity
Browse Source

[chordpro][WIP] Les lignes sont correctement analysées

pull/70/head
Louis 10 years ago
committed by Luthaf
parent
eefcbd2bd2
commit
5d0d0d7000
4 changed files with 184 additions and 103 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 17
      patacrep/songs/chordpro/__init__.py
  2. 46
      patacrep/songs/chordpro/lexer.py
  3. 88
      patacrep/songs/chordpro/parser.py
  4. 136
      patacrep/songs/chordpro/syntax.py

17
patacrep/songs/chordpro/__init__.py
View File

@ -1,8 +1,23 @@
from patacrep import encoding
from patacrep.songs import Song from patacrep.songs import Song
from patacrep.songs.chordpro.syntax import parse_song
class ChordproSong(Song): class ChordproSong(Song):
pass """Chordpros song parser."""
def parse(self):
"""Parse content, and return the dictinory of song data."""
with encoding.open_read(self.fullpath, encoding=self.encoding) as song:
self.data = parse_song(song.read(), self.fullpath)
print(self.data)
import sys; sys.exit(1)
self.titles = self.data['@titles']
del self.data['@titles']
self.languages = self.data['@languages']
del self.data['@languages']
self.authors = self.data['by']
del self.data['by']
SONG_PARSERS = { SONG_PARSERS = {
'sgc': ChordproSong, 'sgc': ChordproSong,

46
patacrep/songs/chordpro/lexer.py
View File

@ -7,15 +7,16 @@ LOGGER = logging.getLogger()
#pylint: disable=invalid-name #pylint: disable=invalid-name
tokens = ( tokens = (
'LBRACKET', #'LBRACKET',
'RBRACKET', #'RBRACKET',
'CHORD',
'LBRACE', 'LBRACE',
'RBRACE', 'RBRACE',
'NEWLINE', 'NEWLINE',
'COLON', #'COLON',
'WORD', 'WORD',
'SPACE', 'SPACE',
'NUMBER' #'NUMBER',
) )
class ChordProLexer: class ChordProLexer:
@ -23,12 +24,15 @@ class ChordProLexer:
tokens = tokens tokens = tokens
t_LBRACKET = r'\[' states = (
t_RBRACKET = r'\]' ('chord', 'exclusive'),
)
t_LBRACE = r'{' t_LBRACE = r'{'
t_RBRACE = r'}' t_RBRACE = r'}'
t_SPACE = r'[ \t]+' t_SPACE = r'[ \t]+'
t_COLON = r':' #t_COLON = r':'
t_chord_CHORD = r'[A-G7#m]+' # TODO This can be refined
def __init__(self): def __init__(self):
self.__class__.lexer = lex.lex(module=self) self.__class__.lexer = lex.lex(module=self)
@ -41,23 +45,37 @@ class ChordProLexer:
return token return token
@staticmethod @staticmethod
def t_comment(token): def t_COMMENT(token):
r'\#.*' r'\#.*'
pass pass
@staticmethod @staticmethod
def t_WORD(token): def t_WORD(token):
r'[a-zA-Z_]+[.,;:!?]?' r'[^\n\][\t ]+'
return token return token
@staticmethod def t_LBRACKET(self, token):
def t_NUMBER(token): r'\['
r'[0-9]+' self.lexer.push_state('chord')
token.value = int(token.value)
return token def t_chord_RBRACKET(self, token):
r'\]'
self.lexer.pop_state()
#@staticmethod
#def t_NUMBER(token):
# r'[0-9]+'
# token.value = int(token.value)
# return token
@staticmethod @staticmethod
def t_error(token): def t_error(token):
"""Manage errors""" """Manage errors"""
LOGGER.error("Illegal character '{}'".format(token.value[0])) LOGGER.error("Illegal character '{}'".format(token.value[0]))
token.lexer.skip(1) token.lexer.skip(1)
@staticmethod
def t_chord_error(token):
"""Manage errors"""
LOGGER.error("Illegal character '{}' in chord..".format(token.value[0]))
token.lexer.skip(1)

88
patacrep/songs/chordpro/parser.py
View File

@ -1,88 +0,0 @@
# -*- coding: utf-8 -*-
"""ChordPro parser"""
import logging
import ply.yacc as yacc
from patacrep.songs.chordpro.lexer import tokens, ChordProLexer
from patacrep.songs.chordpro import ast
from patacrep.errors import SongbookError
LOGGER = logging.getLogger()
class ParsingError(SongbookError):
"""Parsing error."""
def __init__(self, message):
super().__init__(self)
self.message = message
def __str__(self):
return self.message
class Parser:
"""ChordPro parser class"""
def __init__(self, filename=None):
self.tokens = tokens
self.filename = filename
@staticmethod
def __find_column(token):
"""Return the column of ``token``."""
last_cr = token.lexer.lexdata.rfind('\n', 0, token.lexpos)
if last_cr < 0:
last_cr = 0
column = (token.lexpos - last_cr) + 1
return column
def p_error(self, token):
"""Manage parsing errors."""
LOGGER.error("Error in file {}, line {}:{}.".format(
str(self.filename),
token.lineno,
self.__find_column(token),
)
)
@staticmethod
def p_expression(symbols):
"""expression : brackets expression
| braces expression
| command expression
| NEWLINE expression
| word expression
| SPACE expression
| empty
"""
if len(symbols) == 3:
if symbols[2] is None:
symbols[0] = ast.Expression(symbols[1])
else:
symbols[0] = symbols[2].prepend(symbols[1])
else:
symbols[0] = None
@staticmethod
def p_empty(__symbols):
"""empty :"""
return None
@staticmethod
def p_brackets(symbols):
"""brackets : LBRACKET expression RBRACKET"""
symbols[0] = symbols[2]
@staticmethod
def p_braces(symbols):
"""braces : LBRACE expression COLON expression RBRACE"""
symbols[0] = symbols[2]
def parsesong(string, filename=None):
"""Parse song and return its metadata."""
return yacc.yacc(module=Parser(filename)).parse(
string,
lexer=ChordProLexer().lexer,
)

136
patacrep/songs/chordpro/syntax.py
View File

@ -0,0 +1,136 @@
# -*- coding: utf-8 -*-
"""ChordPro parser"""
import logging
import ply.yacc as yacc
from patacrep.songs.chordpro.lexer import tokens, ChordProLexer
from patacrep.songs.chordpro import ast
from patacrep.errors import SongbookError
LOGGER = logging.getLogger()
class ParsingError(SongbookError):
"""Parsing error."""
def __init__(self, message):
super().__init__(self)
self.message = message
def __str__(self):
return self.message
class Parser:
"""ChordPro parser class"""
def __init__(self, filename=None):
self.tokens = tokens
self.filename = filename
@staticmethod
def __find_column(token):
"""Return the column of ``token``."""
last_cr = token.lexer.lexdata.rfind('\n', 0, token.lexpos)
if last_cr < 0:
last_cr = 0
column = (token.lexpos - last_cr) + 1
return column
def p_error(self, token):
"""Manage parsing errors."""
if token: # TODO remove this test
LOGGER.error("Error in file {}, line {}:{}.".format(
str(self.filename),
token.lineno,
self.__find_column(token),
)
)
@staticmethod
def p_song(symbols):
"""song : block song
| empty
"""
if len(symbols) == 2:
symbols[0] = ('song')
else:
symbols[0] = ('song', symbols[1], symbols[2])
@staticmethod
def p_block(symbols):
"""block : directive NEWLINE newlines
| stanza NEWLINE newlines
"""
symbols[0] = ('block', symbols[1])
@staticmethod
def p_newlines(symbols):
"""newlines : NEWLINE newlines
| empty"""
symbols[0] = ('newlines')
@staticmethod
def p_directive(symbols):
"""directive : LBRACE WORD RBRACE"""
symbols[0] = ('directive', symbols[1])
@staticmethod
def p_line(symbols):
"""line : WORD line_next
| CHORD line_next
| SPACE line_next
"""
symbols[0] = ('line', symbols[1], symbols[2])
@staticmethod
def p_line_next(symbols):
"""line_next : WORD line_next
| SPACE line_next
| CHORD line_next
| empty
"""
if len(symbols) == 2:
symbols[0] = ('line-next')
else:
symbols[0] = ('line-next', symbols[1], symbols[2])
@staticmethod
def p_stanza(symbols):
"""stanza : line NEWLINE stanza_next
"""
symbols[0] = ('stanza', symbols[1], symbols[3])
@staticmethod
def p_stanza_next(symbols):
"""stanza_next : line NEWLINE stanza_next
| empty
"""
if len(symbols) == 2:
symbols[0] = ('stanza-next')
else:
symbols[0] = ('stanza-next', symbols[1], symbols[3])
#@staticmethod
#def p_braces(symbols):
# """braces : LBRACE expression COLON expression RBRACE"""
# symbols[0] = symbols[2]
@staticmethod
def p_empty(symbols):
"""empty :"""
symbols[0] = None
#@staticmethod
#def p_comment(symbols):
# """comment : COMMENT"""
# symbols[0] = ('comment', symbols[1])
def parse_song(content, filename=None):
"""Parse song and return its metadata."""
return yacc.yacc(module=Parser(filename)).parse(
content,
lexer=ChordProLexer().lexer,
)
Write Preview
Loading…
Cancel
Save