fbtxt-parser 0.9.0 → 0.9.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (49) hide show
  1. checksums.yaml +4 -4
  2. data/CHANGELOG.md +1 -1
  3. data/Manifest.txt +0 -37
  4. data/README.md +4 -8
  5. data/Rakefile +2 -1
  6. data/lib/fbtxt/parser/parse_tree-match.rb +3 -1
  7. data/lib/fbtxt/parser/parse_tree-props.rb +39 -10
  8. data/lib/fbtxt/parser/parser-top.rb +0 -9
  9. data/lib/fbtxt/parser/parser.rb +879 -843
  10. data/lib/fbtxt/parser/version.rb +1 -1
  11. data/lib/fbtxt/parser.rb +14 -82
  12. metadata +18 -41
  13. data/lib/fbtxt/parser/debuggable.rb +0 -53
  14. data/lib/fbtxt/parser/lexer-logger.rb +0 -20
  15. data/lib/fbtxt/parser/lexer-on_goal.rb +0 -167
  16. data/lib/fbtxt/parser/lexer-on_group_def.rb +0 -31
  17. data/lib/fbtxt/parser/lexer-on_prop_lineup.rb +0 -79
  18. data/lib/fbtxt/parser/lexer-on_prop_misc.rb +0 -123
  19. data/lib/fbtxt/parser/lexer-on_prop_penalties.rb +0 -40
  20. data/lib/fbtxt/parser/lexer-on_round_def.rb +0 -37
  21. data/lib/fbtxt/parser/lexer-on_top.rb +0 -133
  22. data/lib/fbtxt/parser/lexer-prep_doc.rb +0 -131
  23. data/lib/fbtxt/parser/lexer-prep_line.rb +0 -63
  24. data/lib/fbtxt/parser/lexer-tokenize.rb +0 -468
  25. data/lib/fbtxt/parser/lexer.rb +0 -231
  26. data/lib/fbtxt/parser/lexer_buffer.rb +0 -68
  27. data/lib/fbtxt/parser/lexer_token.rb +0 -126
  28. data/lib/fbtxt/parser/token-date--helpers.rb +0 -130
  29. data/lib/fbtxt/parser/token-date--names.rb +0 -108
  30. data/lib/fbtxt/parser/token-date.rb +0 -200
  31. data/lib/fbtxt/parser/token-date_duration.rb +0 -171
  32. data/lib/fbtxt/parser/token-geo.rb +0 -134
  33. data/lib/fbtxt/parser/token-goals--helpers.rb +0 -114
  34. data/lib/fbtxt/parser/token-goals.rb +0 -306
  35. data/lib/fbtxt/parser/token-group.rb +0 -29
  36. data/lib/fbtxt/parser/token-note.rb +0 -40
  37. data/lib/fbtxt/parser/token-prop.rb +0 -309
  38. data/lib/fbtxt/parser/token-prop_name.rb +0 -83
  39. data/lib/fbtxt/parser/token-round.rb +0 -88
  40. data/lib/fbtxt/parser/token-score--helpers.rb +0 -189
  41. data/lib/fbtxt/parser/token-score.rb +0 -60
  42. data/lib/fbtxt/parser/token-score_full.rb +0 -331
  43. data/lib/fbtxt/parser/token-score_fuller.rb +0 -434
  44. data/lib/fbtxt/parser/token-score_legs.rb +0 -59
  45. data/lib/fbtxt/parser/token-status.rb +0 -192
  46. data/lib/fbtxt/parser/token-status_inline.rb +0 -112
  47. data/lib/fbtxt/parser/token-text.rb +0 -221
  48. data/lib/fbtxt/parser/token-time.rb +0 -144
  49. data/lib/fbtxt/parser/token.rb +0 -224
data/lib/fbtxt/parser/token-group.rb DELETED
@@ -1,29 +0,0 @@
1
- module Fbtxt
2
- class Lexer
3
-
4
-
5
- ###
6
- # check for start of group def line e.g.
7
- # Group A | ...
8
- # Group 1 : ....
9
- # Group A2 | ....
10
- ## note - use \A (instead of ^) - \A strictly matches the start of the string.
11
-
12
- START_WITH_GROUP_DEF_LINE_RE = %r{
13
- \A
14
- [ ]* ## ignore leading spaces (if any)
15
- (?<group_def>
16
- Group
17
- [ ]
18
- [a-z0-9]+ ## todo/check - allow dot (.) too e.g. 1.A etc.- why? why not?
19
- )
20
- ### positive lookahead MUST be : OR |
21
- (?= [ ]*
22
- [:|]
23
- [ ]) ## note: requires space for now after [:|] - keep - why? why not?
24
- }ix
25
-
26
-
27
-
28
- end # class Lexer
29
- end # module Fbtxt
data/lib/fbtxt/parser/token-note.rb DELETED
@@ -1,40 +0,0 @@
1
- module Fbtxt
2
- class Lexer
3
-
4
-
5
- ### fix - use (?<text>) - text capture for inner text!!
6
- ## use (?<note> for complete match as a convention!! )
7
- NOTE_RE = %r{
8
- \[
9
- (?<note>
10
- [^\[\]\#]*? ## note - non-greedy/lazy operator
11
- ## exclude comments inside note block - why? why not?
12
- )
13
- \]
14
- }xi
15
-
16
-
17
- ####
18
- ## fix - change NOTE_RE to MATCH_NOTE_RE !!!!
19
- ## and change NOTA_BENE_RE to NOTE_RE !!!
20
-
21
-
22
-
23
- ## check for "literal" (multi-line) note blocks
24
- ## eg. nb: or note:
25
- ## space required after double colon - why? why not?
26
- ##
27
- ## note - use \A (instead of ^) - \A strictly matches the start of the string.
28
- NOTA_BENE_RE = %r{ \A
29
- [ ]* ## ignore leading spaces (if any)
30
- (?: nb | note) [ ]* : [ ]+
31
- (?<nota_bene>
32
- .+? ## use non-greedy
33
- )
34
- [ ]* ## ignore trailing spaces (if any)
35
- \z
36
- }xi
37
-
38
-
39
- end # class Lexer
40
- end # module Fbtxt
data/lib/fbtxt/parser/token-prop.rb DELETED
@@ -1,309 +0,0 @@
1
- ###
2
- ## team prop mode e.g.
3
- ##
4
- ##
5
- ## Fri Jun 14 21:00 @ München Fußball Arena, München
6
- ## Germany v Scotland 5-1 (3-0)
7
- ## (Wirtz 10' Musiala 19' Havertz 45+1' (pen.) Füllkrug 68' Can 90+3'; Rüdiger 87' (o.g.))
8
- ##
9
- ## Germany: Neuer - Kimmich, Rüdiger, Tah [Y], Mittelstädt - Andrich [Y] (Groß 46'),
10
- ## Kroos (Can 80') - Musiala (Müller 74'), Gündogan, Wirtz (Sane 63') -
11
- ## Havertz (Füllkrug 63')
12
- ## Scotland: Gunn - Porteous [R 44'], Hendry, Tierney (McKenna 78') - Ralston [Y],
13
- ## McTominay, McGregor (Gilmour 67'), Robertson - Christie (Shankland 82'),
14
- ## Adams (Hanley 46'), McGinn (McLean 67')
15
-
16
-
17
- module Fbtxt
18
- class Lexer
19
-
20
-
21
- ##############
22
- # add support for props/ attributes e.g.
23
- #
24
- # Germany: Neuer - Kimmich, Rüdiger, Tah [Y], Mittelstädt - Andrich [Y] (46' Groß),
25
- # Kroos (80' Can) - Musiala (74' Müller), Gündogan,
26
- # Wirtz (63' Sane) - Havertz (63' Füllkrug)
27
- # Scotland: Gunn - Porteous [R 44'], Hendry, Tierney (78' McKenna) - Ralston [Y],
28
- # McTominay, McGregor (67' Gilmour), Robertson - Christie (82' Shankland),
29
- # Adams (46' Hanley), McGinn (67' McLean)
30
- #
31
- ## note: colon (:) MUST be followed by one (or more) spaces
32
- ## make sure mon feb 12 18:10 will not match
33
- ## allow 1. FC Köln etc.
34
- ## Mainz 05:
35
- ## limit to 30 chars max
36
- ## only allow chars incl. intl but (NOT ()[]/;)
37
- ##
38
- ##
39
- ## note - use special \G - Matches first matching position !!!!
40
- ## check for \G like backreference of regex tokens/parts if possible/available in ruby?
41
-
42
-
43
-
44
- ## (i) starting w/ letters
45
- ## note - incl./allows digits (0-9)
46
- ## e.g. a1, a2000, etc.
47
- ##
48
- ## note - added back optional trailing dot (.) for abbrev. word !!!
49
- PROP_KEY_WORD_ = %r{
50
- \p{L}
51
- [\p{L}\d]*
52
- \.?
53
- }ix
54
-
55
- ## note - incl. optional dot or numsign e.g. 1. or 1°
56
- PROP_KEY_NUM_ = %r{
57
- \d+
58
- [.°]?
59
- }ix
60
-
61
- ## e.g. 1A, 1FC etc.
62
- ## note - no trailing dot (.) for now - check if any cases exist in real world
63
- PROP_KEY_NUMALPHA_ = %r{
64
- \d+
65
- \p{L}
66
- [\p{L}\d]*
67
- }ix
68
-
69
-
70
-
71
-
72
-
73
- START_WITH_PROP_KEY_RE = %r{
74
- \A ## note - MUST start line; leading spaces optional (eat-up)
75
- (?<prop_key>
76
- [ ]* ## optional leading spaces
77
- (?<key>
78
- (?:
79
- ## (i) starting w/ letters
80
- #{PROP_KEY_WORD_}
81
-
82
- ## (ii) starting w/ number
83
- ## e.g. 1fc, 1a,
84
- | #{PROP_KEY_NUMALPHA_}
85
- ## followed by optional dot) and
86
- ## optional space
87
- ## MUST be follow by letter (a to z)!!!!
88
- ## eg. 1[ fc], 1.[ fc], 1.[fc], etc.
89
- | #{PROP_KEY_NUM_} (?= [ ]? \p{L})
90
- )
91
- (?:
92
- ## connectors - note - no dot (.), must match with abbrev word or num!!
93
- (?: ## (i) single space or WITHOUT surrounding spaces!! - slash (/), dash (-)
94
- ## e.g. do NOT match one - two or one / two
95
- ## only one-two or one/two
96
-
97
- [ /-]
98
-
99
- ## (ii) surrounded by leading or trailing optional space
100
- ## c & a, etc.
101
- ## d'ivoire, d' ivoire
102
- ## borusia 'gladbach etc.
103
- ## exclude space ' space - why? why not? (or ignore for now)
104
- ##
105
- ## check for quotes ('') - not realy supported here
106
- ## e.g. leading or trailing ' will NOT match
107
-
108
- | [ ]? & [ ]?
109
- | [ ]? '
110
- | ' [ ]?
111
-
112
- #### (iii)
113
- ## note - special "hack" to connect WITHOUT space
114
- ## for Union 1.FC and SKN St.Pölten or St.Pölten
115
- ## connects 1.FC => NUM+WORD
116
- ## 1°Mayo => NUM+WORD
117
- ## St.Pölten => ABBREV+WORD
118
- ##
119
- ## note - match WITHOUT (space) connector
120
- ## 1.FC (Union 1.FC Stein)
121
- ## [WORD: "Union"], [NUM: "1."], [WORD: "FC"]
122
- ## St.Pölten (SKN St.Pölten)
123
- ## [WORD: "SKN"], [ABBREV: "St."], [WORD: "Pölten"]
124
- | (?<= [.°] )
125
- (?= \p{L})
126
- )
127
- (?:
128
- #{PROP_KEY_NUMALPHA_}
129
- | #{PROP_KEY_NUM_}
130
- | #{PROP_KEY_WORD_}
131
- )
132
- )*
133
- ) ## close <key> capture
134
- [ ]*? ## slurp trailing spaces
135
- :
136
-
137
- ## positive lookahead (must be followed by space!!)
138
- ## or allow end-of-line too
139
- (?= [ ]+|$)
140
- ) ## close <prop_key> capture
141
- }ix
142
-
143
-
144
-
145
-
146
-
147
- ################
148
- ## todo/check - use token for card short cuts?
149
- ## if m[:name] == 'Y'
150
- ## [:YELLOW_CARD, m[:name]]
151
- ## elsif m[:name] == 'R'
152
- ## [:RED_CARD, m[:name]]
153
- ## - [Y], [R], [Y/R] Yellow-Red Card
154
- ## check if minutes possible inside [Y 46']
155
- ## add [c] for captain too
156
-
157
-
158
- ## [c] or [C] for marking player as captain
159
- ## support [y ] too - or require Y - why? why not?
160
- INLINE_CAPTAIN = %r{ (?<inline_captain>
161
- \[ [cC] \]
162
- )}x
163
-
164
- INLINE_YELLOW = %r{ (?<inline_yellow>
165
- \[ [yY]
166
- ## optional minute
167
- (?: [ ]+
168
- (?<minute> \d{1,3})
169
- '?
170
- (?:
171
- \+
172
- (?<offset>\d{1,2})
173
- '?
174
- )?
175
- )?
176
- \]
177
- )}x
178
-
179
- INLINE_RED = %r{ (?<inline_red>
180
- \[ [rR]
181
- ## optional minute
182
- (?: [ ]+
183
- (?<minute> \d{1,3})
184
- '?
185
- (?:
186
- \+
187
- (?<offset>\d{1,2})
188
- '?
189
- )?
190
- )?
191
- \]
192
- )}x
193
-
194
- INLINE_YELLOW_RED = %r{ (?<inline_yellow_red>
195
- \[ (?:y/r |
196
- Y/R )
197
- ## optional minute
198
- (?: [ ]+
199
- (?<minute> \d{1,3})
200
- '?
201
- (?:
202
- \+
203
- (?<offset>\d{1,2})
204
- '?
205
- )?
206
- )?
207
- \]
208
- )}x
209
-
210
-
211
-
212
-
213
- ### simple prop key for inline use e.g.
214
- ### Coach: or Trainer: or ... add more here later
215
-
216
- PROP_KEY_INLINE_RE = %r{
217
- \b
218
- (?<prop_key> ## note: use prop_key (NOT prop_key_inline or such)
219
- (?<key>
220
- \p{L}+
221
- )
222
- ## note - NO spaces allowed for key for now!!!
223
- :
224
- ## possitive lookahead (must be followed by space!!)
225
- (?=[ ]+)
226
- )
227
- }ix
228
-
229
-
230
-
231
- ## note allow underscore inline e.g.
232
- ## 5_000
233
- ## discuss/check - allow space inline (e.g. 5 000) - why? why not?
234
-
235
- PROP_NUM_RE = %r{
236
- \b
237
- (?<num>
238
- (?<value> [0-9]+
239
- (?: _ [0-9]+)*
240
- )
241
- )
242
- \b
243
- }x
244
-
245
-
246
- ### todo/fix - allow more chars in enclosed name - why? why not?
247
- ## e.g. (') - Cote D'Ivore etc.
248
- ## change to PAREN_NAME or PARENTHESIS or such - why? why not?
249
- ENCLOSED_NAME_RE = %r{
250
- (?<enclosed_name>
251
- \(
252
- (?<name>
253
- \p{L}+
254
- (?:
255
- [ ]
256
- \p{L}+
257
- )*
258
- )
259
- \)
260
- )
261
- }ix
262
-
263
-
264
-
265
-
266
- ###
267
- ## e.g. -; ... or
268
- ## None - ... or
269
- CARDS_NONE_LEFT_RE = %r{ (?<cards_none_left>
270
- ## (i) w/ semicolon (;)
271
- (?: (?: - | \bnone)
272
- [ ]* ;
273
- )
274
- ## (ii) w/ dash (-)
275
- | (?: (?: ∅ | \bnone)
276
- [ ]+ - ## space REQUIRED
277
- (?=[ ]|\z) ## positive lookahead - speace required
278
- )
279
- )}ix
280
-
281
- ## e.g ... ;-
282
- ## or ... ; None
283
- CARDS_NONE_RIGHT_RE = %r{ (?<cards_none_right>
284
- ## (i) w/ semicolon (;)
285
- (?: ; [ ]*
286
- (?: - | none\b)
287
- )
288
- ## (ii) w/ dash (-)
289
- | (?:
290
- (?<=[ ]) ## positive lookbehind - space required
291
- - [ ]+ ## space REQUIRED
292
- (?: ∅ | none\b)
293
- )
294
- )}ix
295
-
296
-
297
- CARDS_SEP_ALT_RE = %r{(?<cards_sep_alt>
298
- (?<=[ ]) ## positive lookbehind - space required
299
- -
300
- (?=[ ]|\z) ## positive lookahead - speace required
301
- )}x
302
-
303
-
304
-
305
-
306
-
307
-
308
- end # class Lexer
309
- end # module Fbtxt
data/lib/fbtxt/parser/token-prop_name.rb DELETED
@@ -1,83 +0,0 @@
1
- module Fbtxt
2
- class Lexer
3
-
4
-
5
- ##
6
- ## see token-text for TEXT_RE
7
- ## change PROP_NAME_RE to TEXT_II or TEXT_??? - why? why not?
8
- ### no do NO change
9
- ## change TEXT_RE to TEAM_RE or TEAM_NAME_RE !!!!
10
- ## it is NOT generic TEXT regex!!!
11
-
12
-
13
-
14
-
15
- PROP_NAME_WORD_ = %r{
16
- \p{L}+
17
- \.? ## optional dot
18
- }ix
19
-
20
-
21
- ## todo/fix - remove support for double quotes e.g. "Rodri" - why? why not?
22
- ##
23
-
24
- ## name different from text (**does NOT allow number in name/text**)
25
- ## different from PROP_KEY too
26
- PROP_NAME_RE = %r{
27
- (?<prop_name>
28
- \b
29
- (?<name>
30
- #{PROP_NAME_WORD_}
31
-
32
- ## connectors
33
- (?:
34
- ## (i) space - only one single space allowed inline!!!
35
- (?:
36
- ### check if negative lookbehind is redudant!!
37
- ## next char is \p{L} and NOT space
38
- ## thus double space not possible!!
39
- (?<! [ ]) ## use negative lookbehind
40
- [ ]
41
- (?= \p{L}|['"]\p{L}) ## use lookahead
42
- )
43
- ## (ii) support (inline) quoted name e.g. "Rodri" or such
44
- | (?:
45
- (?<=[ ]) ## use positive lookbehind
46
- " \p{L}+ "
47
- ## require space here too - why? why not?
48
- )
49
- ## (iii) dash (-)
50
- | (?:
51
- ## use POSITIVE lookBEHIND
52
- ## note - allow leading dot (.) e.g. K.-H.Förster
53
- ## short for Karl-Heinz Förster
54
- ##
55
- ## change to negative lookBEHIND [ '"-]
56
- ## \p{L}\. | \p{L} - not MUST be fixed size
57
- (?<=
58
- [\p{L}.]
59
- )
60
- [-] ## must be surrounded by letters
61
- ## e.g. One-Two NOT
62
- ## One- Two or One - Two or One -Two etc.
63
- (?= \p{L}) ## use lookahead
64
- )
65
- |
66
- (?: ## flex rule for quote - allow any
67
- ## only check for double quotes e.g. cannot follow other ' for now - why? why not?
68
- ## allows rodrigez 'rodri' for example
69
- (?<!') ## use negative lookbehind
70
- '
71
- )
72
- | ## standard case with letter(s) and optional dot
73
- #{PROP_NAME_WORD_}
74
- )*
75
- )
76
- ## add lookahead - must be non-alphanum
77
- ## add colon (:) too - why? why not?
78
- (?= [ ,;\]\)]|$)
79
- )}ix
80
-
81
-
82
- end # class Lexer
83
- end # module Fbtxt
data/lib/fbtxt/parser/token-round.rb DELETED
@@ -1,88 +0,0 @@
1
- module Fbtxt
2
- class Lexer
3
-
4
- ####
5
- #
6
- ## note - use \A (instead of ^) - \A strictly matches the start of the string.
7
- ##
8
- ## todo - add support for trailing markers e.g.
9
- ## ▪ Round 1 ▪▪▪▪▪▪▪▪
10
- ## :: Round 1 ::::::::::::
11
- ##
12
- ## check - allow without space (like in heading =Heading 1=) - why? why not?
13
- ## ▪Round 1▪▪▪▪▪▪▪▪
14
- ## ::Round 1::::::::::::
15
-
16
- ROUND_OUTLINE_I_RE = %r{ \A
17
- [ ]* ## ignore leading spaces (if any)
18
- (?<round_marker>
19
- [▪]{1,3} ## BLACK SMALL SQUARE e.g. ▪,▪▪,▪▪▪
20
- )
21
- [ ]+
22
- (?<round_outline>
23
- ## must start with letter - why? why not?
24
- ### 1st round
25
- ## allow numbers e.g. Group A - 1
26
- ##
27
- ## note - CANNOT incl. :| !!!
28
- ## used for markers for defs/definitions
29
- [^:|]+? ## use non-greedy
30
- )
31
- (?:
32
- [ ]+
33
- [▪]+
34
- )?
35
- [ ]* ## ignore trailing spaces (if any)
36
- \z
37
- }xi
38
-
39
- ROUND_OUTLINE_II_RE = %r{ \A
40
- [ ]* ## ignore leading spaces (if any)
41
- (?<round_marker>
42
- ::{1,3} ## e.g. ::,:::,::::
43
- )
44
- [ ]+
45
- (?<round_outline>
46
- ## must start with letter - why? why not?
47
- ### 1st round
48
- ## allow numbers e.g. Group A - 1
49
- ##
50
- ## note - CANNOT incl. :| !!!
51
- ## used for markers for defs/definitions
52
- [^:|]+? ## use non-greedy
53
- )
54
- (?:
55
- [ ]+
56
- ::+
57
- )?
58
- [ ]* ## ignore trailing spaces (if any)
59
- \z
60
- }xi
61
-
62
- ROUND_OUTLINE_RE = Regexp.union( ROUND_OUTLINE_I_RE,
63
- ROUND_OUTLINE_II_RE,
64
- )
65
-
66
-
67
- ###
68
- # note - for def(initions) only one level support
69
- # that is, no round outline additions possible (e.g ▪▪ 1st leg etc.)
70
- ROUND_DEF_OUTLINE_RE = %r{ \A
71
- [ ]* ## ignore leading spaces (if any)
72
- (?: [▪] ## BLACK SMALL SQUARE
73
- |
74
- :: )
75
- [ ]+
76
- (?<round_outline>
77
- [^:|]+? ## use non-greedy
78
- )
79
- [ ]* ## ignore trailing spaces (if any)
80
- ### possitive lookahead MUST be : OR |
81
- (?= [:|]
82
- [ ]) ## note: requires space for now after [:|] - keep - why? why not?
83
- }ix
84
-
85
-
86
-
87
- end # class Lexer
88
- end # module Fbtxt