1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
|
from journal_lib.parse.lexwrapper import LexWrapper
class JournalLexer(LexWrapper):
states = (
('sHEADER', 'exclusive'), # Entry header parsing state
('sHEADEREFF', 'exclusive'), # Entry header effective date parsing state
('sENTRY', 'exclusive'), # Entry parsing state
('sENTRYCONTENT', 'exclusive'), # Entry parsing state
('sBLOCKCOMMENT', 'exclusive'), # Block comment parsing state
('sACCOUNT', 'exclusive'), # Account definition parsing state
('sCOMMODITY', 'exclusive'), # Commodity definition parsing state
)
reserved = {
"account": 'KW_ACCOUNT',
"commodity": 'KW_COMMODITY'
}
kw_state_map = {
"KW_ACCOUNT": "sACCOUNT",
"KW_COMMODITY": "sCOMMODITY",
}
tokens = (
'TEXT',
'AMOUNT',
'COMMODITY',
'COMMENT',
'INLINE_COMMENT',
'DATE',
'ENTRY_STATUS',
'ENTRY_EFFECTIVE_DATE_SEPARATOR',
'COMMODITY_NOTE',
'COMMODITY_FORMAT',
'COMMODITY_NOMARKET',
'COMMODITY_DEFAULT',
) + tuple(reserved.values())
t_ANY_ignore = " \t"
literals = "\n"
# Rules for the 'initial' state
def t_INITIAL_DATE(self, t):
r"\d{4}(-|\/)\d{2}(-|\/)\d{2}"
self._state_begin("sHEADER", t)
return t
def t_INITIAL_eof(self, t):
pass
def t_INITIAL_COMMENT(self, t):
r"(;|\#|\%|\||\*).+\n"
t.value = t.value.lstrip()
if t.value[0] in [";", "#", "%", "|", "*"]:
t.value = t.value[1:]
pass
def t_INITIAL_BLOCKCOMMENT(self, t):
r"comment"
self._state_begin("sBLOCKCOMMENT", t)
def t_INITIAL_KEYWORD(self, t):
r"[a-zA-Z_][a-zA-Z_0-9]*"
t.type = self.reserved.get(t.value, "KW")
if (new_state := self.kw_state_map.get(t.type)) is not None:
self._state_begin(new_state, t)
return t
# Rules for the 'sBLOCKCOMMENT' state
def t_sBLOCKCOMMENT_end(self, t):
r"end\scomment"
t.lexer.lineno += t.value.count("\n")
self._state_begin("INITIAL", t)
def t_sBLOCKCOMMENT_content(self, t):
r".+?\n"
def t_sBLOCKCOMMENT_error(self, t):
r.lexer.skip(1)
# Rules for the 'sACCOUNT' state
def t_sACCOUNT_TEXT(self, t):
r'("[^"]+")|([^\n;]+)'
if t.value.startswith('"') and t.value.endswith('"'):
t.value = t.value[1:-1]
t.value = t.value.rstrip()
return t
def t_sACCOUNT_COMMENT(self, t):
r"(;)[^\n]*"
t.value.lstrip()
if t.value[0] == ";":
t.value = t.value[1:]
return t
def t_sACCOUNT_newline(self, t):
r"\n"
self._state_begin("INITIAL", t)
# Rules for the 'sCOMMODITY' state
def t_sCOMMODITY_KW(self, t):
r"(note|format|nomarket|default)"
if t.value == "note":
t.type = "COMMODITY_NOTE"
elif t.value == "format":
t.type = "COMMODITY_FORMAT"
elif t.value == "nomarket":
t.type = "COMMODITY_NOMARKET"
elif t.value == "default":
t.type = "COMMODITY_DEFAULT"
return t
def t_sCOMMODITY_TEXT(self, t):
r"[^\n]+"
return t
def t_sCOMMODITY_newline(self, t):
r"\n(?=(\s*\n|\s*$|[^\s]))"
self._state_begin("INITIAL", t)
# Rules for the 'sheader' state
def t_sHEADER_ENTRY_STATUS(self, t):
r"(\*|!)"
return t
def t_sHEADER_ENTRY_EFFECTIVE_DATE_SEPARATOR(self, t):
r"="
self._state_begin("sHEADEREFF", t)
return t
def t_sHEADER_TEXT(self, t):
r"[^\n]+"
if (t.value.startswith('"') and t.value.endswith('"')) or (
t.value.startswith("'") and t.value.endswith("'")
):
t.value = t.value[1:-1]
return t
def t_sHEADER_newline(self, t):
r"\n"
self._state_begin("sENTRY", t)
# Rules for the 'sheader_effective_date' state
def t_sHEADEREFF_DATE(self, t):
r"\d{4}(-|\/)\d{2}(-|\/)\d{2}"
self._state_begin("sHEADER", t)
return t
# Rules for the 'sentry' state
def t_sENTRY_TEXT(self, t):
r"[^\n;]+?(?=\s{2,}|$|;)"
if t.value.startswith('"') and t.value.endswith('"'):
t.value = t.value[1:-1]
t.value = t.value.rstrip()
self._state_begin("sENTRYCONTENT")
return t
# Rules for the 'sENTRYCONTENT' state
def t_sENTRYCONTENT_COMMODITY(self, t):
r"\$|NOK"
return t
def t_sENTRYCONTENT_AMOUNT(self, t):
r"(-)?(\d|\,)+(\.\d{2})?"
t.value = t.value.replace(",", "")
return t
def t_sENTRY_sENTRYCONTENT_COMMENT(self, t):
r";[^\n]*"
# Check if the comment is at the start of a line (considering whitespaces)
line_start = t.lexer.lexdata.rfind("\n", 0, t.lexpos) + 1
pre_comment = t.lexer.lexdata[line_start : t.lexpos]
# Remove the leading characters
t.value = t.value.lstrip(" ;")
# If the comment is at the start of a line, it's a standalone comment
if pre_comment.isspace() or pre_comment == "":
t.type = "COMMENT"
else:
t.type = "INLINE_COMMENT"
return t
def t_sENTRYCONTENT_newline(self, t):
r"\n"
self._state_begin("sENTRY", t)
def t_sENTRY_sENTRYCONTENT_double_newline(self, t):
r"\n\n"
self._state_begin("INITIAL", t)
# Common rules
def t_ANY_eof(self, t):
self._state_begin("INITIAL", t)
def t_ANY_newline(self, t):
r"\n+"
t.lexer.lineno += len(t.value)
def t_ANY_error(self, t):
self._hl_token(t)
t.lexer.skip(1)
|
