alf 0.9.3 → 0.10.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (270) hide show
  1. data/CHANGELOG.md +255 -129
  2. data/Gemfile +31 -1
  3. data/Gemfile.lock +17 -20
  4. data/LICENCE.md +1 -1
  5. data/Manifest.txt +2 -0
  6. data/README.md +37 -43
  7. data/TODO.md +1 -1
  8. data/alf.gemspec +10 -7
  9. data/alf.noespec +24 -13
  10. data/bin/alf +2 -2
  11. data/doc/commands/exec.md +16 -0
  12. data/doc/commands/help.md +11 -0
  13. data/doc/commands/main.md +33 -0
  14. data/doc/commands/show.md +19 -0
  15. data/doc/operators/non_relational/autonum.md +23 -0
  16. data/doc/operators/non_relational/clip.md +31 -0
  17. data/doc/operators/non_relational/coerce.md +15 -0
  18. data/doc/operators/non_relational/compact.md +20 -0
  19. data/doc/operators/non_relational/defaults.md +32 -0
  20. data/doc/operators/non_relational/generator.md +20 -0
  21. data/doc/operators/non_relational/sort.md +24 -0
  22. data/doc/operators/relational/extend.md +18 -0
  23. data/doc/operators/relational/group.md +27 -0
  24. data/doc/operators/relational/intersect.md +13 -0
  25. data/doc/operators/relational/join.md +27 -0
  26. data/doc/operators/relational/matching.md +20 -0
  27. data/doc/operators/relational/minus.md +12 -0
  28. data/doc/operators/relational/not-matching.md +20 -0
  29. data/doc/operators/relational/project.md +28 -0
  30. data/doc/operators/relational/quota.md +21 -0
  31. data/doc/operators/relational/rank.md +27 -0
  32. data/doc/operators/relational/rename.md +17 -0
  33. data/doc/operators/relational/restrict.md +25 -0
  34. data/doc/operators/relational/summarize.md +25 -0
  35. data/doc/operators/relational/ungroup.md +20 -0
  36. data/doc/operators/relational/union.md +14 -0
  37. data/doc/operators/relational/unwrap.md +20 -0
  38. data/doc/operators/relational/wrap.md +24 -0
  39. data/examples/csv/suppliers.csv +6 -0
  40. data/examples/logs/access.log +1000 -0
  41. data/examples/logs/combined.alf +2 -0
  42. data/examples/logs/hits.alf +14 -0
  43. data/examples/logs/not_found.alf +7 -0
  44. data/examples/logs/robots-cheating.alf +11 -0
  45. data/examples/logs/robots.alf +8 -0
  46. data/examples/northwind/customers.csv +92 -0
  47. data/examples/northwind/northwind.db +0 -0
  48. data/examples/northwind/orders.csv +831 -0
  49. data/examples/operators/clip.alf +1 -1
  50. data/examples/operators/database.alf +5 -6
  51. data/examples/operators/defaults.alf +1 -1
  52. data/examples/operators/group.alf +1 -1
  53. data/examples/operators/project.alf +2 -1
  54. data/examples/operators/pseudo-with.alf +2 -2
  55. data/examples/operators/quota.alf +2 -2
  56. data/examples/operators/summarize.alf +2 -2
  57. data/lib/alf/aggregator/aggregators.rb +77 -0
  58. data/lib/alf/aggregator/base.rb +95 -0
  59. data/lib/alf/aggregator/class_methods.rb +57 -0
  60. data/lib/alf/buffer/sorted.rb +48 -0
  61. data/lib/alf/command/class_methods.rb +27 -0
  62. data/lib/alf/command/doc_manager.rb +72 -0
  63. data/lib/alf/command/exec.rb +12 -0
  64. data/lib/alf/command/help.rb +31 -0
  65. data/lib/alf/command/main.rb +146 -0
  66. data/lib/alf/command/show.rb +33 -0
  67. data/lib/alf/environment/base.rb +37 -0
  68. data/lib/alf/environment/class_methods.rb +93 -0
  69. data/lib/alf/environment/explicit.rb +38 -0
  70. data/lib/alf/environment/folder.rb +62 -0
  71. data/lib/alf/extra/csv.rb +104 -0
  72. data/lib/alf/extra/logs.rb +100 -0
  73. data/lib/alf/extra/sequel.rb +77 -0
  74. data/lib/alf/{yaml.rb → extra/yaml.rb} +0 -0
  75. data/lib/alf/extra.rb +5 -0
  76. data/lib/alf/iterator/base.rb +38 -0
  77. data/lib/alf/iterator/class_methods.rb +22 -0
  78. data/lib/alf/iterator/proxy.rb +33 -0
  79. data/lib/alf/lispy/instance_methods.rb +157 -0
  80. data/lib/alf/operator/base.rb +74 -0
  81. data/lib/alf/operator/binary.rb +32 -0
  82. data/lib/alf/operator/cesure.rb +45 -0
  83. data/lib/alf/operator/class_methods.rb +132 -0
  84. data/lib/alf/operator/experimental.rb +9 -0
  85. data/lib/alf/operator/non_relational/autonum.rb +24 -0
  86. data/lib/alf/operator/non_relational/clip.rb +20 -0
  87. data/lib/alf/operator/non_relational/coerce.rb +21 -0
  88. data/lib/alf/operator/non_relational/compact.rb +62 -0
  89. data/lib/alf/operator/non_relational/defaults.rb +25 -0
  90. data/lib/alf/operator/non_relational/generator.rb +38 -0
  91. data/lib/alf/operator/non_relational/sort.rb +23 -0
  92. data/lib/alf/operator/nullary.rb +20 -0
  93. data/lib/alf/operator/relational/extend.rb +24 -0
  94. data/lib/alf/operator/relational/group.rb +32 -0
  95. data/lib/alf/operator/relational/intersect.rb +37 -0
  96. data/lib/alf/operator/relational/join.rb +106 -0
  97. data/lib/alf/operator/relational/matching.rb +45 -0
  98. data/lib/alf/operator/relational/minus.rb +37 -0
  99. data/lib/alf/operator/relational/not_matching.rb +45 -0
  100. data/lib/alf/operator/relational/project.rb +22 -0
  101. data/lib/alf/operator/relational/quota.rb +51 -0
  102. data/lib/alf/operator/relational/rank.rb +55 -0
  103. data/lib/alf/operator/relational/rename.rb +19 -0
  104. data/lib/alf/operator/relational/restrict.rb +20 -0
  105. data/lib/alf/operator/relational/summarize.rb +83 -0
  106. data/lib/alf/operator/relational/ungroup.rb +25 -0
  107. data/lib/alf/operator/relational/union.rb +32 -0
  108. data/lib/alf/operator/relational/unwrap.rb +21 -0
  109. data/lib/alf/operator/relational/wrap.rb +22 -0
  110. data/lib/alf/operator/shortcut.rb +53 -0
  111. data/lib/alf/operator/signature.rb +262 -0
  112. data/lib/alf/operator/transform.rb +27 -0
  113. data/lib/alf/operator/unary.rb +38 -0
  114. data/lib/alf/reader/alf_file.rb +24 -0
  115. data/lib/alf/reader/base.rb +119 -0
  116. data/lib/alf/reader/class_methods.rb +82 -0
  117. data/lib/alf/reader/rash.rb +28 -0
  118. data/lib/alf/relation/class_methods.rb +37 -0
  119. data/lib/alf/relation/instance_methods.rb +127 -0
  120. data/lib/alf/renderer/base.rb +72 -0
  121. data/lib/alf/renderer/class_methods.rb +58 -0
  122. data/lib/alf/renderer/rash.rb +19 -0
  123. data/lib/alf/{text.rb → renderer/text.rb} +1 -1
  124. data/lib/alf/tools/coerce.rb +14 -0
  125. data/lib/alf/tools/miscellaneous.rb +77 -0
  126. data/lib/alf/tools/to_lispy.rb +99 -0
  127. data/lib/alf/tools/to_ruby_literal.rb +14 -0
  128. data/lib/alf/tools/tuple_handle.rb +50 -0
  129. data/lib/alf/types/attr_list.rb +56 -0
  130. data/lib/alf/types/attr_name.rb +28 -0
  131. data/lib/alf/types/boolean.rb +12 -0
  132. data/lib/alf/types/heading.rb +96 -0
  133. data/lib/alf/types/ordering.rb +93 -0
  134. data/lib/alf/types/renaming.rb +57 -0
  135. data/lib/alf/types/summarization.rb +76 -0
  136. data/lib/alf/types/tuple_computation.rb +61 -0
  137. data/lib/alf/types/tuple_expression.rb +61 -0
  138. data/lib/alf/types/tuple_predicate.rb +49 -0
  139. data/lib/alf/version.rb +2 -2
  140. data/lib/alf.rb +193 -3714
  141. data/spec/integration/__database__/group.alf +1 -1
  142. data/spec/integration/__database__/suppliers_csv.csv +6 -0
  143. data/spec/integration/command/alf/alf.db +0 -0
  144. data/spec/integration/command/alf/alf_env_sqlite.cmd +1 -0
  145. data/spec/integration/command/alf/alf_env_sqlite.stdout +9 -0
  146. data/spec/integration/command/alf/alf_help.cmd +1 -0
  147. data/spec/integration/command/alf/alf_help.stdout +67 -0
  148. data/spec/integration/command/autonum/autonum_0.cmd +1 -1
  149. data/spec/integration/command/coerce/coerce_1.cmd +1 -0
  150. data/spec/integration/command/coerce/coerce_1.stdout +5 -0
  151. data/spec/integration/command/defaults/defaults_0.cmd +1 -1
  152. data/spec/integration/command/defaults/defaults_0.stdout +9 -9
  153. data/spec/integration/command/defaults/defaults_2.cmd +1 -0
  154. data/spec/integration/command/defaults/defaults_2.stdout +9 -0
  155. data/spec/integration/command/generator/generator_1.cmd +1 -0
  156. data/spec/integration/command/generator/generator_1.stdout +10 -0
  157. data/spec/integration/command/generator/generator_2.cmd +1 -0
  158. data/spec/integration/command/generator/generator_2.stdout +5 -0
  159. data/spec/integration/command/generator/generator_3.cmd +1 -0
  160. data/spec/integration/command/generator/generator_3.stdout +5 -0
  161. data/spec/integration/command/group/group_0.cmd +1 -1
  162. data/spec/integration/command/group/group_1.cmd +1 -1
  163. data/spec/integration/command/help/help_1.cmd +1 -0
  164. data/spec/integration/command/help/help_1.stdout +22 -0
  165. data/spec/integration/command/quota/quota_0.cmd +1 -1
  166. data/spec/integration/command/rank/rank_1.cmd +1 -1
  167. data/spec/integration/command/rank/rank_1.stdout +10 -10
  168. data/spec/integration/command/rank/rank_2.cmd +1 -1
  169. data/spec/integration/command/rank/rank_2.stdout +10 -10
  170. data/spec/integration/command/rank/rank_3.cmd +1 -1
  171. data/spec/integration/command/rank/rank_3.stdout +10 -10
  172. data/spec/integration/command/rank/rank_4.cmd +1 -1
  173. data/spec/integration/command/rank/rank_5.cmd +1 -1
  174. data/spec/integration/command/show/show_csv.cmd +1 -0
  175. data/spec/integration/command/show/show_csv.stdout +6 -0
  176. data/spec/integration/command/show/show_rash_2.cmd +1 -1
  177. data/spec/integration/command/show/show_rash_2.stdout +5 -5
  178. data/spec/integration/command/sort/sort_0.cmd +1 -1
  179. data/spec/integration/command/sort/sort_1.cmd +1 -1
  180. data/spec/integration/command/sort/sort_1.stdout +2 -2
  181. data/spec/integration/command/sort/sort_2.cmd +1 -0
  182. data/spec/integration/command/sort/sort_2.stdout +9 -0
  183. data/spec/integration/command/sort/sort_3.cmd +1 -0
  184. data/spec/integration/command/sort/sort_3.stdout +9 -0
  185. data/spec/integration/command/summarize/summarize_0.cmd +1 -1
  186. data/spec/integration/command/ungroup/ungroup_0.cmd +1 -1
  187. data/spec/integration/command/wrap/wrap_0.cmd +1 -1
  188. data/spec/integration/semantics/test_project.alf +5 -6
  189. data/spec/integration/semantics/test_rank.alf +16 -16
  190. data/spec/integration/test_command.rb +17 -6
  191. data/spec/integration/test_examples.rb +1 -1
  192. data/spec/regression/logs/apache_combined.log +5 -0
  193. data/spec/regression/logs/test_path_attribute.rb +25 -0
  194. data/spec/regression/relation/test_relation_allbut_all.rb +14 -0
  195. data/spec/shared/an_operator_class.rb +10 -5
  196. data/spec/spec_helper.rb +1 -7
  197. data/spec/unit/assumptions/test_set.rb +64 -0
  198. data/spec/unit/command/doc_manager/dynamic.md +1 -0
  199. data/spec/unit/command/doc_manager/example.md +1 -0
  200. data/spec/unit/command/doc_manager/example_1.txt +11 -0
  201. data/spec/unit/command/doc_manager/static.md +1 -0
  202. data/spec/unit/command/doc_manager/test_call.rb +49 -0
  203. data/spec/unit/csv/input.csv +3 -0
  204. data/spec/unit/csv/test_reader.rb +66 -0
  205. data/spec/unit/csv/test_renderer.rb +73 -0
  206. data/spec/unit/lispy/test_relation.rb +37 -0
  207. data/spec/unit/lispy/test_run.rb +40 -0
  208. data/spec/unit/lispy/test_tuple.rb +36 -0
  209. data/spec/unit/logs/apache_combined.log +5 -0
  210. data/spec/unit/logs/postgresql.log +29 -0
  211. data/spec/unit/logs/test_reader.rb +56 -0
  212. data/spec/unit/operator/non_relational/compact/{buffer_based.rb → test_buffer_based.rb} +0 -0
  213. data/spec/unit/operator/non_relational/test_clip.rb +1 -1
  214. data/spec/unit/operator/non_relational/test_coerce.rb +35 -0
  215. data/spec/unit/operator/non_relational/test_defaults.rb +15 -2
  216. data/spec/unit/operator/non_relational/test_generator.rb +78 -0
  217. data/spec/unit/operator/relational/join/test_hash_based.rb +4 -4
  218. data/spec/unit/operator/relational/matching/test_hash_based.rb +6 -6
  219. data/spec/unit/operator/relational/not_matching/test_hash_based.rb +4 -4
  220. data/spec/unit/operator/relational/summarize/test_hash_based.rb +10 -6
  221. data/spec/unit/operator/relational/summarize/test_sort_based.rb +18 -7
  222. data/spec/unit/operator/relational/test_group.rb +8 -8
  223. data/spec/unit/operator/relational/test_intersect.rb +3 -3
  224. data/spec/unit/operator/relational/test_minus.rb +3 -3
  225. data/spec/unit/operator/relational/test_project.rb +12 -2
  226. data/spec/unit/operator/relational/test_quota.rb +5 -6
  227. data/spec/unit/operator/relational/test_summarize.rb +9 -11
  228. data/spec/unit/operator/relational/test_union.rb +1 -1
  229. data/spec/unit/operator/relational/test_wrap.rb +1 -1
  230. data/spec/unit/operator/signature/test_collect_on.rb +45 -0
  231. data/spec/unit/operator/signature/test_initialize.rb +17 -0
  232. data/spec/unit/operator/signature/test_install.rb +56 -0
  233. data/spec/unit/operator/signature/test_option_parser.rb +36 -0
  234. data/spec/unit/operator/signature/test_parse_args.rb +60 -0
  235. data/spec/unit/operator/signature/test_parse_argv.rb +87 -0
  236. data/spec/unit/operator/signature/test_to_lispy.rb +102 -0
  237. data/spec/unit/operator/signature/test_to_shell.rb +103 -0
  238. data/spec/unit/operator/test_non_relational.rb +3 -1
  239. data/spec/unit/relation/test_relops.rb +20 -15
  240. data/spec/unit/sequel/alf.db +0 -0
  241. data/spec/unit/sequel/test_environment.rb +54 -0
  242. data/spec/unit/test_aggregator.rb +32 -22
  243. data/spec/unit/test_environment.rb +5 -0
  244. data/spec/unit/test_lispy.rb +4 -0
  245. data/spec/unit/test_relation.rb +5 -0
  246. data/spec/unit/text/test_cell.rb +6 -6
  247. data/spec/unit/text/test_row.rb +3 -3
  248. data/spec/unit/text/test_table.rb +6 -6
  249. data/spec/unit/tools/test_coalesce.rb +15 -0
  250. data/spec/unit/tools/test_coerce.rb +10 -0
  251. data/spec/unit/tools/test_to_lispy.rb +138 -0
  252. data/spec/unit/tools/test_to_ruby_literal.rb +10 -0
  253. data/spec/unit/tools/test_tuple_handle.rb +1 -59
  254. data/spec/unit/types/test_attr_list.rb +106 -0
  255. data/spec/unit/types/test_attr_name.rb +52 -0
  256. data/spec/unit/{test_heading.rb → types/test_heading.rb} +10 -0
  257. data/spec/unit/types/test_ordering.rb +127 -0
  258. data/spec/unit/types/test_renaming.rb +55 -0
  259. data/spec/unit/types/test_summarization.rb +63 -0
  260. data/spec/unit/types/test_tuple_computation.rb +60 -0
  261. data/spec/unit/types/test_tuple_expression.rb +64 -0
  262. data/spec/unit/types/test_tuple_predicate.rb +79 -0
  263. data/tasks/debug_mail.rake +1 -1
  264. data/tasks/debug_mail.txt +5 -0
  265. data/tasks/gh-pages.rake +63 -0
  266. metadata +325 -52
  267. data/spec/unit/operator/test_command_methods.rb +0 -38
  268. data/spec/unit/tools/test_ordering_key.rb +0 -94
  269. data/spec/unit/tools/test_parse_commandline_args.rb +0 -47
  270. data/spec/unit/tools/test_projection_key.rb +0 -83
@@ -0,0 +1,157 @@
1
+ module Alf
2
+ module Lispy
3
+
4
+ alias :ruby_extend :extend
5
+
6
+ # The environment
7
+ attr_accessor :environment
8
+
9
+ #
10
+ # Compiles a query expression given by a String or a block and returns
11
+ # the result (typically a tuple iterator)
12
+ #
13
+ # Example
14
+ #
15
+ # # with a string
16
+ # op = compile "(restrict :suppliers, lambda{ city == 'London' })"
17
+ #
18
+ # # or with a block
19
+ # op = compile {
20
+ # (restrict :suppliers, lambda{ city == 'London' })
21
+ # }
22
+ #
23
+ # @param [String] expr a Lispy expression to compile
24
+ # @return [Iterator] the iterator resulting from compilation
25
+ #
26
+ def compile(expr = nil, path = nil, &block)
27
+ if expr.nil?
28
+ instance_eval(&block)
29
+ else
30
+ b = _clean_binding
31
+ (path ? Kernel.eval(expr, b, path) : Kernel.eval(expr, b))
32
+ end
33
+ end
34
+
35
+ #
36
+ # Evaluates a query expression given by a String or a block and returns
37
+ # the result as an in-memory relation (Alf::Relation)
38
+ #
39
+ # Example:
40
+ #
41
+ # # with a string
42
+ # rel = evaluate "(restrict :suppliers, lambda{ city == 'London' })"
43
+ #
44
+ # # or with a block
45
+ # rel = evaluate {
46
+ # (restrict :suppliers, lambda{ city == 'London' })
47
+ # }
48
+ #
49
+ def evaluate(expr = nil, path = nil, &block)
50
+ compiled = compile(expr, path, &block)
51
+ case compiled
52
+ when Iterator
53
+ compiled.to_rel
54
+ else
55
+ compiled
56
+ end
57
+ end
58
+
59
+ #
60
+ # Coerces `h` to a valid tuple.
61
+ #
62
+ # @param [Hash] h, a hash mapping symbols to values
63
+ #
64
+ def Tuple(h)
65
+ unless h.keys.all?{|k| k.is_a?(Symbol)} &&
66
+ h.values.all?{|v| !v.nil?}
67
+ raise ArgumentError, "Invalid tuple literal #{h.inspect}"
68
+ end
69
+ h
70
+ end
71
+
72
+ #
73
+ # Coerces `args` to a valid relation.
74
+ #
75
+ def Relation(first, *args)
76
+ if args.empty?
77
+ if first.is_a?(Symbol)
78
+ environment.dataset(first).to_rel
79
+ elsif first.is_a?(Hash)
80
+ Alf::Relation[first]
81
+ else
82
+ raise ArgumentError, "Unable to coerce `#{first.inspect}` to a relation"
83
+ end
84
+ else
85
+ Alf::Relation[*args.unshift(first)]
86
+ end
87
+ end
88
+
89
+ #
90
+ # Install the DSL through iteration over defined operators
91
+ #
92
+ Operator.each do |op_class|
93
+ meth_name = Tools.ruby_case(Tools.class_name(op_class)).to_sym
94
+ if op_class.unary?
95
+ define_method(meth_name) do |child, *args|
96
+ child = Iterator.coerce(child, environment)
97
+ op_class.new(*args).pipe(child, environment)
98
+ end
99
+ elsif op_class.binary?
100
+ define_method(meth_name) do |left, right, *args|
101
+ operands = [left, right].collect{|x| Iterator.coerce(x, environment)}
102
+ op_class.new(*args).pipe(operands, environment)
103
+ end
104
+ elsif op_class.nullary?
105
+ define_method(meth_name) do |*args|
106
+ op_class.new(*args).pipe(nil, environment)
107
+ end
108
+ else
109
+ raise "Unexpected operator #{op_class}"
110
+ end
111
+ end # Operators::each
112
+
113
+ #
114
+ # Install the DSL through iteration over defined aggregators
115
+ #
116
+ Aggregator.each do |agg_class|
117
+ agg_name = Tools.ruby_case(Tools.class_name(agg_class)).to_sym
118
+ if method_defined?(agg_name)
119
+ raise "Unexpected method clash on Lispy: #{agg_name}"
120
+ else
121
+ define_method(agg_name) do |*args, &block|
122
+ agg_class.new(*args, &block)
123
+ end
124
+ end
125
+ end
126
+
127
+ def allbut(child, attributes)
128
+ (project child, attributes, :allbut => true)
129
+ end
130
+
131
+ #
132
+ # Runs a command as in shell.
133
+ #
134
+ # Example:
135
+ #
136
+ # lispy = Alf.lispy(Alf::Environment.examples)
137
+ # op = lispy.run(['restrict', 'suppliers', '--', "city == 'Paris'"])
138
+ #
139
+ def run(argv, requester = nil)
140
+ argv = Quickl.parse_commandline_args(argv) if argv.is_a?(String)
141
+ argv = Quickl.split_commandline_args(argv, '|')
142
+ argv.inject(nil) do |cmd,arr|
143
+ arr.shift if arr.first == "alf"
144
+ main = Alf::Command::Main.new(environment)
145
+ main.stdin_reader = cmd unless cmd.nil?
146
+ main.run(arr, requester)
147
+ end
148
+ end
149
+
150
+ private
151
+
152
+ def _clean_binding
153
+ binding
154
+ end
155
+
156
+ end # module Lispy
157
+ end # module Alf
@@ -0,0 +1,74 @@
1
+ module Alf
2
+ module Operator
3
+ #
4
+ # Contains all methods for operator instances
5
+ #
6
+ module Base
7
+
8
+ #
9
+ # Input datasets
10
+ #
11
+ attr_accessor :datasets
12
+
13
+ #
14
+ # Optional environment
15
+ #
16
+ attr_accessor :environment
17
+
18
+ #
19
+ # Create an operator instance
20
+ #
21
+ def initialize(*args)
22
+ signature.parse_args(args, self)
23
+ end
24
+
25
+ #
26
+ # Sets the operator input
27
+ #
28
+ def pipe(input, env = environment)
29
+ raise NotImplementedError, "Operator#pipe should be overriden"
30
+ end
31
+
32
+ #
33
+ # Returns operator signature.
34
+ #
35
+ def signature
36
+ self.class.signature
37
+ end
38
+
39
+ #
40
+ # Yields each tuple in turn
41
+ #
42
+ # This method is implemented in a way that ensures that all operators are
43
+ # thread safe. It is not intended to be overriden, use _each instead.
44
+ #
45
+ def each
46
+ op = self.dup
47
+ op._prepare
48
+ op._each(&Proc.new)
49
+ end
50
+
51
+ protected
52
+
53
+ #
54
+ # Prepares the iterator before subsequent call to _each.
55
+ #
56
+ # This method is intended to be overriden by suclasses to install what's
57
+ # need for successful iteration. The default implementation does nothing.
58
+ #
59
+ def _prepare
60
+ end
61
+
62
+ # Internal implementation of the iterator.
63
+ #
64
+ # This method must be implemented by subclasses. It is safe to use instance
65
+ # variables (typically initialized in _prepare) here.
66
+ #
67
+ def _each
68
+ end
69
+
70
+ private :datasets=, :environment=
71
+ end # module Base
72
+ include Base
73
+ end # module Operator
74
+ end # module Alf
@@ -0,0 +1,32 @@
1
+ module Alf
2
+ module Operator
3
+ #
4
+ # Specialization of Operator for operators that work on a binary input
5
+ #
6
+ module Binary
7
+ include Operator
8
+
9
+ #
10
+ # Sets the operator input
11
+ #
12
+ def pipe(input, env = environment)
13
+ self.environment = env
14
+ self.datasets = input
15
+ self
16
+ end
17
+
18
+ protected
19
+
20
+ # Returns the left operand
21
+ def left
22
+ Iterator.coerce(datasets.first, environment)
23
+ end
24
+
25
+ # Returns the right operand
26
+ def right
27
+ Iterator.coerce(datasets.last, environment)
28
+ end
29
+
30
+ end # module Binary
31
+ end # module Operator
32
+ end # module Alf
@@ -0,0 +1,45 @@
1
+ module Alf
2
+ module Operator
3
+ #
4
+ # Specialization of Operator for implementing operators that rely on a
5
+ # cesure algorithm.
6
+ #
7
+ module Cesure
8
+ include Unary
9
+
10
+ protected
11
+
12
+ # (see Operator#_each)
13
+ def _each
14
+ receiver, prev_key = Proc.new, nil
15
+ each_input_tuple do |tuple|
16
+ cur_key = project(tuple)
17
+ if cur_key != prev_key
18
+ flush_cesure(prev_key, receiver) unless prev_key.nil?
19
+ start_cesure(cur_key, receiver)
20
+ prev_key = cur_key
21
+ end
22
+ accumulate_cesure(tuple, receiver)
23
+ end
24
+ flush_cesure(prev_key, receiver) unless prev_key.nil?
25
+ end
26
+
27
+ # Projects a given tuple and returns it's cesure projection
28
+ def project(tuple)
29
+ end
30
+
31
+ # Callback fired every time a new block starts
32
+ def start_cesure(key, receiver)
33
+ end
34
+
35
+ # Callback fired on each tuple of the current block
36
+ def accumulate_cesure(tuple, receiver)
37
+ end
38
+
39
+ # Callback fired at end of a block
40
+ def flush_cesure(key, receiver)
41
+ end
42
+
43
+ end # module Cesure
44
+ end # module Operator
45
+ end # module Alf
@@ -0,0 +1,132 @@
1
+ module Alf
2
+ module Operator
3
+ #
4
+ # Encapsulates method that allows making operator introspection, that is,
5
+ # knowing operator cardinality and similar stuff.
6
+ #
7
+ module ClassMethods
8
+
9
+ #
10
+ # Returns false
11
+ #
12
+ def command?
13
+ false
14
+ end
15
+
16
+ #
17
+ # Returns true
18
+ #
19
+ def operator?
20
+ true
21
+ end
22
+
23
+ #
24
+ # Returns true if this is a relational operator, false otherwise
25
+ #
26
+ def relational?
27
+ ancestors.include?(Relational)
28
+ end
29
+
30
+ #
31
+ # Returns true if this is a non relational operator, false otherwise
32
+ #
33
+ def non_relational?
34
+ ancestors.include?(NonRelational)
35
+ end
36
+
37
+ #
38
+ # Runs the command on commandline arguments
39
+ #
40
+ # @param [Array] argv an array of commandline arguments, typically ARGV
41
+ # @param [Object] req an optional requester, typically a super command
42
+ # @return [Iterator] an Iterator with query result
43
+ #
44
+ def run(argv, req = nil)
45
+ inst, operands = from_argv(argv)
46
+
47
+ # find standard input reader
48
+ stdin_reader = if req && req.respond_to?(:stdin_reader)
49
+ req.stdin_reader
50
+ else
51
+ Reader.coerce($stdin)
52
+ end
53
+
54
+ # normalize operands
55
+ operands = [ stdin_reader ] + Array(operands)
56
+ operands = operands.collect{|op|
57
+ Iterator.coerce(op, req && req.environment)
58
+ }
59
+ operands = if nullary?
60
+ []
61
+ elsif unary?
62
+ operands.last
63
+ elsif binary?
64
+ operands[-2..-1]
65
+ end
66
+
67
+ inst.pipe(operands, req && req.environment)
68
+ inst
69
+ end
70
+
71
+ #
72
+ # Returns true if this operator is a zero-ary operator, false otherwise
73
+ #
74
+ def nullary?
75
+ ancestors.include?(Operator::Nullary)
76
+ end
77
+
78
+ #
79
+ # Returns true if this operator is an unary operator, false otherwise
80
+ #
81
+ def unary?
82
+ ancestors.include?(Operator::Unary)
83
+ end
84
+
85
+ #
86
+ # Returns true if this operator is a binary operator, false otherwise
87
+ #
88
+ def binary?
89
+ ancestors.include?(Operator::Binary)
90
+ end
91
+
92
+ #
93
+ # Installs or set the operator signature
94
+ #
95
+ def signature
96
+ if block_given?
97
+ @signature = Signature.new(self, &Proc.new)
98
+ @signature.install
99
+ options do |opt|
100
+ signature.fill_option_parser(opt, self)
101
+ end
102
+ else
103
+ @signature ||= Signature.new(self)
104
+ end
105
+ end
106
+
107
+ private
108
+
109
+ # Factors an operator instance from commandline arguments
110
+ def from_argv(argv)
111
+ inst = new
112
+ operands = inst.signature.parse_argv(argv, inst)
113
+ [inst, operands]
114
+ end
115
+
116
+ end # module ClassMethods
117
+
118
+ #
119
+ # Yields non-relational then relational operators, in turn.
120
+ #
121
+ def self.each
122
+ Operator::NonRelational.each{|x| yield(x)}
123
+ Operator::Relational.each{|x| yield(x)}
124
+ end
125
+
126
+ # Ensures that the Introspection module is set on real operators
127
+ def self.included(mod)
128
+ mod.extend(ClassMethods) if mod.is_a?(Class)
129
+ end
130
+
131
+ end # module Operator
132
+ end # module Alf
@@ -0,0 +1,9 @@
1
+ module Alf
2
+ module Operator
3
+ #
4
+ # Marker for experimental operators
5
+ #
6
+ module Experimental
7
+ end # module Experimental
8
+ end # module Operator
9
+ end # module Alf
@@ -0,0 +1,24 @@
1
+ module Alf
2
+ module Operator::NonRelational
3
+ class Autonum < Alf::Operator()
4
+ include Operator::NonRelational, Operator::Transform
5
+
6
+ signature do |s|
7
+ s.argument :as, AttrName, :autonum
8
+ end
9
+
10
+ protected
11
+
12
+ # (see Operator#_prepare)
13
+ def _prepare
14
+ @autonum = -1
15
+ end
16
+
17
+ # (see Operator::Transform#_tuple2tuple)
18
+ def _tuple2tuple(tuple)
19
+ tuple.merge(@as => (@autonum += 1))
20
+ end
21
+
22
+ end # class Autonum
23
+ end # module Operator::NonRelational
24
+ end # module Alf
@@ -0,0 +1,20 @@
1
+ module Alf
2
+ module Operator::NonRelational
3
+ class Clip < Alf::Operator()
4
+ include Operator::NonRelational, Operator::Transform
5
+
6
+ signature do |s|
7
+ s.argument :attributes, AttrList, []
8
+ s.option :allbut, Boolean, false, "Apply an allbut clipping?"
9
+ end
10
+
11
+ protected
12
+
13
+ # (see Operator::Transform#_tuple2tuple)
14
+ def _tuple2tuple(tuple)
15
+ @attributes.project(tuple, @allbut)
16
+ end
17
+
18
+ end # class Clip
19
+ end # module Operator::NonRelational
20
+ end # module Alf
@@ -0,0 +1,21 @@
1
+ module Alf
2
+ module Operator::NonRelational
3
+ class Coerce < Alf::Operator()
4
+ include Operator::NonRelational, Operator::Transform
5
+
6
+ signature do |s|
7
+ s.argument :heading, Heading, {}
8
+ end
9
+
10
+ protected
11
+
12
+ # (see Operator::Transform#_tuple2tuple)
13
+ def _tuple2tuple(tuple)
14
+ tuple.merge tuple_collect(@heading.attributes){|k,d|
15
+ [k, coerce(tuple[k], d)]
16
+ }
17
+ end
18
+
19
+ end # class Coerce
20
+ end # module Operator::NonRelational
21
+ end # module Alf
@@ -0,0 +1,62 @@
1
+ module Alf
2
+ module Operator::NonRelational
3
+ class Compact < Alf::Operator()
4
+ include Operator::NonRelational, Operator::Shortcut, Operator::Unary
5
+
6
+ signature do |s|
7
+ end
8
+
9
+ # Removes duplicates according to a complete order
10
+ class SortBased
11
+ include Operator, Operator::Cesure
12
+
13
+ def initialize
14
+ @cesure_key ||= AttrList.new([])
15
+ end
16
+
17
+ protected
18
+
19
+ # (see Operator::Cesure#project)
20
+ def project(tuple)
21
+ @cesure_key.project(tuple, true)
22
+ end
23
+
24
+ # (see Operator::Cesure#accumulate_cesure)
25
+ def accumulate_cesure(tuple, receiver)
26
+ @tuple = tuple
27
+ end
28
+
29
+ # (see Operator::Cesure#flush_cesure)
30
+ def flush_cesure(key, receiver)
31
+ receiver.call(@tuple)
32
+ end
33
+
34
+ end # class SortBased
35
+
36
+ # Removes duplicates by loading all in memory and filtering
37
+ # them there
38
+ class BufferBased
39
+ include Operator, Operator::Unary
40
+
41
+ protected
42
+
43
+ def _prepare
44
+ @tuples = input.to_a.uniq
45
+ end
46
+
47
+ def _each
48
+ @tuples.each(&Proc.new)
49
+ end
50
+
51
+ end # class BufferBased
52
+
53
+ protected
54
+
55
+ def longexpr
56
+ chain BufferBased.new,
57
+ datasets
58
+ end
59
+
60
+ end # class Compact
61
+ end # module Operator::NonRelational
62
+ end # module Alf
@@ -0,0 +1,25 @@
1
+ module Alf
2
+ module Operator::NonRelational
3
+ class Defaults < Alf::Operator()
4
+ include Operator::NonRelational, Operator::Transform
5
+
6
+ signature do |s|
7
+ s.argument :defaults, TupleComputation, {}
8
+ s.option :strict, Boolean, false, "Restrict to default attributes only?"
9
+ end
10
+
11
+ protected
12
+
13
+ # (see Operator::Transform#_tuple2tuple)
14
+ def _tuple2tuple(tuple)
15
+ handle = TupleHandle.new.set(tuple)
16
+ defs = @defaults.evaluate(handle)
17
+ keys = @strict ? defs.keys : (tuple.keys | defs.keys)
18
+ tuple_collect(keys){|k|
19
+ [k, coalesce(tuple[k], defs[k])]
20
+ }
21
+ end
22
+
23
+ end # class Defaults
24
+ end # module Operator::NonRelational
25
+ end # module Alf
@@ -0,0 +1,38 @@
1
+ module Alf
2
+ module Operator::NonRelational
3
+ class Generator < Alf::Operator()
4
+ include Operator::NonRelational, Operator::Nullary
5
+
6
+ class Size < Integer
7
+ extend Myrrha::Domain
8
+
9
+ def self.coerce(args)
10
+ Tools.coerce(args, Integer)
11
+ end
12
+
13
+ def self.from_argv(argv, opts = {})
14
+ coerce(argv.first)
15
+ end
16
+
17
+ def self.predicate
18
+ @predicate ||= lambda{|i| i >= 0}
19
+ end
20
+
21
+ end # Size
22
+
23
+ signature do |s|
24
+ s.argument :size, Size, 10
25
+ s.argument :as, AttrName, :num
26
+ end
27
+
28
+ protected
29
+
30
+ def _each
31
+ size.times do |i|
32
+ yield(@as => i+1)
33
+ end
34
+ end
35
+
36
+ end # class Generator
37
+ end # module Operator::NonRelational
38
+ end # module Alf
@@ -0,0 +1,23 @@
1
+ module Alf
2
+ module Operator::NonRelational
3
+ class Sort < Alf::Operator()
4
+ include Operator::NonRelational, Operator::Unary
5
+
6
+ signature do |s|
7
+ s.argument :ordering, Ordering, []
8
+ end
9
+
10
+ protected
11
+
12
+ def _prepare
13
+ @buffer = Buffer::Sorted.new(ordering)
14
+ @buffer.add_all(input)
15
+ end
16
+
17
+ def _each
18
+ @buffer.each(&Proc.new)
19
+ end
20
+
21
+ end # class Sort
22
+ end # module Operator::NonRelational
23
+ end # module Alf
@@ -0,0 +1,20 @@
1
+ module Alf
2
+ module Operator
3
+ #
4
+ # Specialization of Operator for operators without operands
5
+ #
6
+ module Nullary
7
+ include Operator
8
+
9
+ #
10
+ # Sets the operator input
11
+ #
12
+ def pipe(input, env = environment)
13
+ self.environment = env
14
+ self.datasets = []
15
+ self
16
+ end
17
+
18
+ end # module Nullary
19
+ end # module Operator
20
+ end # module Alf