src/piflow_portable.py
1"""Arrow stream adapters for portable PiFlow components."""
2
3import bisect
4from itertools import islice
5import json
6import math
7import re
8import statistics
9from xml.etree import ElementTree
10
11import pyarrow as pa
12import pyarrow.compute as pc
13import piflow_documents as documents
14import piflow_collections as collections
15import piflow_tabular as tabular
16import piflow_rdf as rdf
17import piflow_workbooks as workbooks
18from xstream_operator import descriptor, preview_process, records_schema, result, run_operator
19
20MAX_INPUT = 8 * 1024 * 1024
21HALF_WIDTH = str.maketrans({**{c: c - 65248 for c in range(0xff01, 0xff5f)}, 0x3000: 32})
22PROVINCES = dict(zip(
23 "beijing tianjin shanghai chongqing anhui fujian gansu guangdong guizhou hainan hebei heilongjiang "
24 "henan hubei hunan jiangsu jiangxi jilin liaoning qinghai shaanxi shanxi shandong sichuan yunnan "
25 "zhejiang inner-mongolia ningxia guangxi xinjiang tibet".split(),
26 "北京 天津 上海 重庆 安徽 福建 甘肃 广东 贵州 海南 河北 黑龙江 河南 湖北 湖南 江苏 江西 吉林 辽宁 "
27 "青海 陕西 山西 山东 四川 云南 浙江 内蒙古自治区 宁夏回族自治区 广西壮族自治区 新疆维吾尔自治区 西藏自治区".split(),
28))
29CLEANERS = {"email_clean", "phone_number_clean", "identity_number_clean", "province_clean", "title_clean"}
30SCALERS = {"max_min_normalization", "scope_normalization", "z_score", "discretization"}
31
32
33def clean(value, operation):
34 if value is None:
35 return "" if operation == "province_clean" else None
36 if not isinstance(value, str):
37 raise ValueError("cleaning columns must contain strings")
38 value = value.translate(HALF_WIDTH)
39 if operation == "title_clean":
40 return value
41 if operation == "email_clean":
42 value = value.lower()
43 return value if re.fullmatch(r"[a-z0-9._%+-]+@[a-z0-9.-]+\.[a-z0-9-]+", value) else ""
44 if operation == "phone_number_clean":
45 value = re.sub("[^0-9]", "", value)
46 return value if re.fullmatch(r"1[34578][0-9]{9}", value) else None
47 if operation == "identity_number_clean":
48 value = re.sub("[^0-9X]", "", value.upper()).lstrip("0")
49 if re.fullmatch("[0-9]{15}", value):
50 return value
51 if re.fullmatch("[0-9]{17}[0-9X]", value):
52 weights = (7, 9, 10, 5, 8, 4, 2, 1, 6, 3, 7, 9, 10, 5, 8, 4, 2)
53 checksum = sum(int(digit) * weight for digit, weight in zip(value, weights))
54 if value[-1] == "10X98765432"[checksum % 11]:
55 return value
56 return None
57 normalized = value.strip().casefold().replace(" ", "-")
58 for pinyin, name in PROVINCES.items():
59 if normalized in {pinyin, name.casefold(), name + "省", name + "市"}:
60 return name
61 if name.endswith("自治区") and normalized in {"内蒙古", "宁夏", "广西", "新疆", "西藏"} and name.startswith(normalized):
62 return name
63 return value
64
65
66def names(text):
67 values = [value.strip() for value in text.split(",")]
68 if not all(values) or len(values) != len(set(values)):
69 raise ValueError("column names must be unique and nonempty")
70 return values
71
72
73def field_indices(schema, columns):
74 indices = [schema.get_field_index(name) for name in columns]
75 if -1 in indices:
76 raise ValueError("input includes an unknown or ambiguous column")
77 return indices
78
79
80def scale_columns(operation, params):
81 if operation == "z_score":
82 ins, outs = names(params["inputCols"]), names(params["outputCols"])
83 if len(ins) != len(outs):
84 raise ValueError("inputCols and outputCols must contain the same number of names")
85 return list(zip(ins, outs))
86 return [(params["inputCol"], params["outputCol"])]
87
88
89def scale(values, operation, params):
90 available = [float(value) for value in values if value is not None]
91 if not all(map(math.isfinite, available)):
92 raise ValueError("scaling requires finite numeric input")
93 if not available:
94 return values
95 if operation == "discretization":
96 count = params["numBins"]
97 if not 2 <= count <= 1000:
98 raise ValueError("numBins must be from 2 to 1000")
99 if params["method"] == "EqualWidth":
100 if any(value < 0 or value > count for value in available):
101 raise ValueError("EqualWidth accepts values from zero through numBins")
102 apply = lambda value: min(int(value), count - 1)
103 elif params["method"] == "EqualFrequency":
104 ordered = sorted(available)
105 cuts = sorted({ordered[min(len(ordered) - 1, math.ceil(len(ordered) * i / count) - 1)]
106 for i in range(1, count)} - {ordered[0], ordered[-1]})
107 apply = lambda value: bisect.bisect_right(cuts, value)
108 else:
109 raise ValueError("method must be EqualWidth or EqualFrequency")
110 else:
111 if operation == "z_score":
112 origin = statistics.mean(available)
113 spread = statistics.stdev(available) if len(available) > 1 else 0
114 else:
115 origin = min(available)
116 spread = max(available) - origin
117 low, high = params["range"] if operation == "scope_normalization" else (0, 1)
118 if not math.isfinite(low) or not math.isfinite(high) or low >= high:
119 raise ValueError("range must have two increasing finite bounds")
120 apply = lambda value: (value - origin) / spread * (high - low) + low if spread else None
121 return [None if value is None else apply(value) for value in values]
122
123
124def replace_column(table, name, values):
125 index = table.schema.get_field_index(name)
126 return table.append_column(name, values) if index < 0 else table.set_column(index, name, values)
127
128
129def collect(chunks):
130 data = bytearray()
131 for chunk in chunks:
132 data.extend(chunk)
133 if len(data) > MAX_INPUT:
134 raise ValueError("input exceeds 8 MiB")
135 return bytes(data)
136
137
138def collect_records(port, schema):
139 batches, size, rows = [], 0, 0
140 for batch in port.records():
141 size += batch.nbytes
142 rows += batch.num_rows
143 if size > MAX_INPUT or rows > 100_000:
144 raise ValueError("batch operation accepts at most 8 MiB and 100,000 records")
145 batches.append(batch)
146 return pa.Table.from_batches(batches, schema=schema)
147
148
149def json_rows(data):
150 def invalid_number(value):
151 raise ValueError("non-finite JSON number: " + value)
152
153 root = json.loads(data, parse_constant=invalid_number)
154 rows = root if isinstance(root, list) else [root]
155 if not all(isinstance(row, dict) for row in rows):
156 raise ValueError("JSON input must be an object or an array of objects")
157 # Arrow's Python row inference reads its columns from the first row.
158 columns = dict.fromkeys(key for row in rows for key in row)
159 return pa.table({column: [row.get(column) for row in rows] for column in columns})
160
161
162class XmlBuilder(ElementTree.TreeBuilder):
163 def doctype(self, name, pubid, system):
164 raise ValueError("XML document types are unsupported")
165
166
167def xml_root(data):
168 if len(data) > MAX_INPUT:
169 raise ValueError("XML exceeds 8 MiB")
170 return ElementTree.fromstring(data, parser=ElementTree.XMLParser(target=XmlBuilder()))
171
172
173def xml_rows(root, operation, params):
174 if operation == "xml_parser":
175 selected = list(root.iter(params["rowTag"]))
176 columns = list(dict.fromkeys(child.tag for row in selected for child in row))
177 else:
178 tags = names(params["label"])
179 if root.tag != tags[0] or len(tags) < 2:
180 raise ValueError("label must start with the root and name a repeated child tag")
181 selected = root.findall("/".join(tags[1:]))
182 columns = names(params["schema"])
183 return pa.table({column: pa.array([row.findtext(column) or None for row in selected], type=pa.string())
184 for column in columns})
185
186
187def xml_model(node, depth=0):
188 if depth >= 32:
189 raise ValueError("XML nesting exceeds 32 levels")
190 if not node.attrib and not len(node):
191 return node.text
192 model = {"@" + name: value for name, value in node.attrib.items()}
193 if node.text and node.text.strip():
194 model["#text"] = node.text
195 groups = {}
196 for child in node:
197 groups.setdefault(child.tag, []).append(xml_model(child, depth + 1))
198 model.update({key: values[0] if len(values) == 1 else values for key, values in groups.items()})
199 return model
200
201
202def parse_xml_column(value):
203 if value is None:
204 return None
205 root = xml_root(value)
206 return json.dumps({root.tag: xml_model(root)}, ensure_ascii=False)
207
208
209def put_xml_row(root, row):
210 target = ElementTree.SubElement(root, "ROW")
211 for name, value in row.items():
212 if not re.fullmatch(r"[a-zA-Z_][a-zA-Z0-9_.-]*", name):
213 raise ValueError("record column is not an XML name: " + name)
214 if isinstance(value, (list, dict)):
215 raise ValueError("XML serialization accepts scalar columns")
216 if value is not None:
217 ElementTree.SubElement(target, name).text = str(value)
218
219
220def emit(ctx, table, port="result"):
221 out = ctx.records_output(port, table.schema)
222 for batch in table.to_batches(max_chunksize=1024):
223 out.write(batch)
224
225
226def emit_tables(ctx, tables):
227 outputs = {name: ctx.records_output(name, table.schema) for name, table in tables.items()}
228 for name, table in tables.items():
229 for batch in table.to_batches(max_chunksize=1024):
230 outputs[name].write(batch)
231
232
233def emit_graph(ctx, edges, vertices):
234 emit_tables(ctx, {
235 "edges": pa.Table.from_pylist(edges, schema=collections.EDGE_SCHEMA),
236 "vertex": pa.Table.from_pylist(vertices, schema=collections.VERTEX_SCHEMA),
237 })
238
239
240def inferred_schema(operation, schema, params):
241 if operation == "word_spliter":
242 return pa.schema([("words", pa.string())])
243 if operation == "average_temperature":
244 return tabular.SENSOR_SCHEMA
245 if operation in {"data_sort", "complement_by_memcache"}:
246 return schema
247 if operation == "field_type_conversion" and schema is not None:
248 return tabular.numeric_schema(schema, params, names)
249 if operation == "convert_schema_type" and schema is not None:
250 return tabular.convert_schema_type(schema, params, names)
251 if operation == "all_fields_clean_neo4j" and schema is not None:
252 return tabular.string_schema(schema)
253 if operation == "person_id_expansion" and schema is not None:
254 removed = [params["expandIDField"], params["expandIDType"]]
255 field_indices(schema, removed)
256 retained = [field for field in schema if field.name not in removed]
257 added = [*collections.ID_FIELDS, "source", "uuid", "id_hash"]
258 if len(set(removed)) != 2 or any(field.name in added for field in retained):
259 raise ValueError("input names conflict with generated identity fields")
260 return pa.schema(retained + [pa.field(name, pa.string()) for name in added], metadata=schema.metadata)
261 if operation == "folder_csv_parser":
262 return pa.schema([(name, pa.string()) for name in names(params["schema"])])
263 if operation == "select_files_by_name":
264 return pa.schema([("path", pa.string())])
265 if operation == "card_code_clean" and schema is not None:
266 field = schema.field(field_indices(schema, [params["cardCodeField"], params["cardTypeField"]])[0])
267 if not pa.types.is_string(field.type):
268 raise ValueError("cardCodeField must be a string column")
269 return schema
270 if operation == "regex_text_process" and schema is not None:
271 column = schema.field(field_indices(schema, [params["columnName"]])[0])
272 if not pa.types.is_string(column.type) or column.name + "_new" in schema.names:
273 raise ValueError("input must be a string column with an unused _new field name")
274 return schema.append(pa.field(column.name + "_new", pa.string()))
275 if operation == "pdf_parser":
276 return pa.schema([("page", pa.int64()), ("text", pa.string())])
277 if operation in {"docx_parser", "html_parser"}:
278 return documents.RECORDS_TEXT
279 if operation == "pptx_parser":
280 return documents.RECORDS_TEXT.append(pa.field("slide", pa.int64()))
281 if operation == "xml_parser_generate_new_field" and schema is not None:
282 field_indices(schema, [params["decoderField"]])
283 name = params["newField"]
284 if not name or name in schema.names:
285 raise ValueError("newField must be nonempty and absent from the input")
286 return schema.append(pa.field(name, pa.string()))
287 if operation in CLEANERS | {"xml_parser_columns"} and schema is not None:
288 columns = params["xmlColumns"] if operation == "xml_parser_columns" else params["columnName"]
289 indices = field_indices(schema, names(columns))
290 if any(not pa.types.is_string(schema.field(i).type) and not pa.types.is_large_string(schema.field(i).type)
291 for i in indices):
292 raise ValueError("selected columns must be strings")
293 return pa.schema([pa.field(field.name, pa.string()) if i in indices else field
294 for i, field in enumerate(schema)], metadata=schema.metadata)
295 if operation in SCALERS and schema is not None:
296 for source, target in scale_columns(operation, params):
297 field = schema.field(field_indices(schema, [source])[0])
298 if not (pa.types.is_integer(field.type) or pa.types.is_floating(field.type)):
299 raise ValueError("scaling requires integer or floating-point columns")
300 for source, target in scale_columns(operation, params):
301 field = pa.field(target, pa.float64())
302 index = schema.get_field_index(target)
303 schema = schema.append(field) if index == -1 else schema.set(index, field)
304 if operation == "json_string_parser":
305 return json_rows(params["jsonString"]).schema
306 if operation == "xml_string_parser":
307 return pa.schema([(column, pa.string()) for column in names(params["schema"])])
308 return schema if operation in CLEANERS | SCALERS | {"xml_parser_columns"} else None
309
310
311def process(ctx, operation):
312 params = ctx.params
313 if operation in {"json_string_parser", "xml_string_parser"}:
314 if operation == "json_string_parser":
315 emit(ctx, json_rows(params["jsonString"]))
316 else:
317 emit(ctx, xml_rows(xml_root(params["XmlString"]), operation, params))
318 return
319 if operation == "excel_parser":
320 emit(ctx, workbooks.first_sheet_collection(ctx, collect))
321 return
322 if operation in collections.FOLDER_OPERATORS:
323 emit(ctx, collections.folder_tables(ctx, operation, params, collect, json_rows, xml_root, xml_rows, names))
324 return
325 if operation == "complement_by_memcache":
326 lookup = ctx.input("lookup")
327 materialized = collect_records(lookup, lookup.schema)
328 tabular.enrich_records(ctx, materialized, ctx.input("source").schema, names)
329 return
330 if operation == "excel_write_multiple_sheets":
331 collections.excel_workbook(ctx, collect_records)
332 return
333 if operation == "label_propagation":
334 edges = ctx.input("edges")
335 edge_rows = collect_records(edges, edges.schema).to_pylist()
336 vertex = ctx.input("vertex")
337 vertex_rows = collect_records(vertex, vertex.schema).to_pylist()
338 labels = collections.label_propagation(edge_rows, vertex_rows, params["maxIter"])
339 emit_graph(ctx, edge_rows, labels)
340 return
341 source = ctx.input("source")
342 if operation == "word_spliter":
343 import jieba
344 import unicodedata
345
346 value = collect(source.bytes()).decode("utf-8-sig")
347 text = "".join(char for char in value if not char.isspace()
348 and not unicodedata.category(char).startswith(("P", "S")))
349 words = ({"words": word} for word in jieba.cut_for_search(text, HMM=False))
350 out = ctx.records_output("result", inferred_schema(operation, None, params))
351 for rows in iter(lambda: list(islice(words, 1024)), []):
352 out.write(pa.RecordBatch.from_pylist(rows, schema=inferred_schema(operation, None, params)))
353 elif operation == "rdf_to_df":
354 emit_tables(ctx, rdf.parse_rdf(collect(source.bytes()), params["syntax"]))
355 elif operation == "excel_write_sort":
356 table = collect_records(source, source.schema)
357 workbooks.write_sorted(ctx, tabular.sorted_table(table, params, names))
358 elif operation == "load_graph":
359 edges, vertices = collections.load_graph(collect(source.bytes()))
360 emit_graph(ctx, edges, vertices)
361 elif operation == "select_files_by_name":
362 schema = inferred_schema(operation, source.schema, params)
363 index = field_indices(source.schema, [params["pathColumn"]])[0]
364 pattern = params["selectionConditions"]
365 if not isinstance(pattern, str) or len(pattern) > 256:
366 raise ValueError("selectionConditions must be a glob up to 256 characters")
367 out = ctx.records_output("result", schema)
368 for batch in source.records():
369 matching = [value for value in batch.column(index).to_pylist() if collections.file_matches(value, pattern)]
370 out.write(pa.RecordBatch.from_arrays([pa.array(matching, type=pa.string())], schema=schema))
371 elif operation == "regex_text_process":
372 schema = inferred_schema(operation, source.schema, params)
373 index = field_indices(schema, [params["columnName"]])[0]
374 pattern, replacement = params["regex"], params["replaceStr"]
375 if len(pattern) > 1024 or len(replacement) > 2048:
376 raise ValueError("regular expression or replacement exceeds its size limit")
377 out = ctx.records_output("result", schema)
378 for batch in source.records():
379 # RE2 executes without backtracking. Limit input and expansion before calling Arrow.
380 column = batch.column(index)
381 widths = pc.binary_length(column).to_pylist()
382 max_bytes = sum((width + 1) * (len(replacement.encode()) + 1) for width in widths if width is not None)
383 if max_bytes > 32 * 1024 * 1024:
384 raise ValueError("potential regex expansion exceeds 32 MiB in one batch")
385 changed = pc.replace_substring_regex(column, pattern, replacement)
386 out.write(pa.RecordBatch.from_arrays([*batch.columns, changed], schema=schema))
387 elif operation in {"data_sort", "average_temperature"}:
388 table = collect_records(source, source.schema)
389 result = tabular.average_temperature(table.to_pylist()) if operation == "average_temperature" else tabular.sorted_table(table, params, names)
390 emit(ctx, result)
391 elif operation in {"field_type_conversion", "convert_schema_type", "all_fields_clean_neo4j"}:
392 schema = inferred_schema(operation, source.schema, params)
393 out = ctx.records_output("result", schema)
394 for batch in source.records():
395 columns = []
396 for index, field in enumerate(schema):
397 column = pc.cast(batch.column(index), field.type)
398 if operation == "all_fields_clean_neo4j":
399 column = pc.replace_substring(column, '"', '')
400 columns.append(column)
401 out.write(pa.RecordBatch.from_arrays(columns, schema=schema))
402 elif operation in {"card_code_clean", "person_id_expansion"}:
403 schema = inferred_schema(operation, source.schema, params)
404 out = ctx.records_output("result", schema)
405 for batch in source.records():
406 rows = batch.to_pylist()
407 if operation == "card_code_clean":
408 for row in rows:
409 if str(row[params["cardTypeField"]]) == "1":
410 key = params["cardCodeField"]
411 row[key] = clean(row[key], "identity_number_clean")
412 else:
413 rows = [collections.expand_id(row, params) for row in rows]
414 out.write(pa.RecordBatch.from_pylist(rows, schema=schema))
415 elif operation in {"docx_parser", "pptx_parser", "html_parser", "pdf_parser", "flatten_xml_parser",
416 "evaluate_json_path", "decompress_gzip"}:
417 data = collect(source.bytes())
418 if operation == "decompress_gzip":
419 out = ctx.bytes_output("result")
420 for chunk in documents.decompress(data):
421 out.write(chunk)
422 return
423 if operation == "html_parser":
424 table = documents.html_text(data)
425 elif operation == "pdf_parser":
426 table = documents.pdf_text(data, inferred_schema(operation, None, params))
427 elif operation in {"docx_parser", "pptx_parser"}:
428 table = documents.office_text(data, operation, xml_root)
429 elif operation == "evaluate_json_path":
430 table = documents.json_field(data, params["tag"], json_rows)
431 else:
432 table = documents.flatten_xml(xml_root(data), params)
433 emit(ctx, table)
434 elif operation == "xml_parser_generate_new_field":
435 schema = inferred_schema(operation, source.schema, params)
436 source_index = schema.get_field_index(params["decoderField"])
437 out = ctx.records_output("result", schema)
438 for batch in source.records():
439 values = [documents.xml_value(value, params["tagXPath"], xml_root)
440 for value in batch.column(source_index).to_pylist()]
441 out.write(pa.RecordBatch.from_arrays([*batch.columns, pa.array(values, type=pa.string())], schema=schema))
442 elif operation in {"json_parser", "xml_parser"}:
443 data = collect(source.bytes())
444 emit(ctx, json_rows(data) if operation == "json_parser" else xml_rows(xml_root(data), operation, params))
445 elif operation == "json_save":
446 out = ctx.bytes_output("result")
447 for batch in source.records():
448 for row in batch.to_pylist():
449 out.write((json.dumps(row, ensure_ascii=False, allow_nan=False) + "\n").encode())
450 elif operation == "xml_save":
451 out = ctx.bytes_output("result")
452 out.write(b"<ROWS>")
453 for batch in source.records():
454 for row in batch.to_pylist():
455 temp = ElementTree.Element("ROWS")
456 put_xml_row(temp, row)
457 out.write(ElementTree.tostring(temp[0], encoding="utf-8"))
458 out.write(b"</ROWS>")
459 elif operation in SCALERS:
460 schema = source.schema
461 inferred_schema(operation, schema, params)
462 original = collect_records(source, schema)
463 table = original
464 for origin, target in scale_columns(operation, params):
465 values = scale(original[origin].to_pylist(), operation, params)
466 table = replace_column(table, target, pa.array(values, type=pa.float64()))
467 emit(ctx, table)
468 else:
469 schema = inferred_schema(operation, source.schema, params)
470 selected = names(params["xmlColumns"] if operation == "xml_parser_columns" else params["columnName"])
471 indices = field_indices(source.schema, selected)
472 out = ctx.records_output("result", schema)
473 for batch in source.records():
474 arrays = list(batch.columns)
475 for index in indices:
476 values = arrays[index].to_pylist()
477 cleaned = (parse_xml_column(value) if operation == "xml_parser_columns" else clean(value, operation)
478 for value in values)
479 arrays[index] = pa.array(cleaned, type=pa.string())
480 out.write(pa.RecordBatch.from_arrays(arrays, schema=schema))
481
482
483def start(operation, output_view):
484 output_views = output_view if isinstance(output_view, dict) else {"result": output_view}
485 def execute(ctx):
486 process(ctx, operation)
487
488 def infer(inputs, params):
489 outputs = {}
490 for port, view in output_views.items():
491 schema = None
492 if view == "records":
493 if operation == "rdf_to_df":
494 schema = rdf.ENTITY if port == "entityOut" else rdf.RELATION
495 elif operation in {"load_graph", "label_propagation"}:
496 schema = collections.EDGE_SCHEMA if port == "edges" else collections.VERTEX_SCHEMA
497 else:
498 source = inputs.get("source")
499 schema = inferred_schema(operation, records_schema(source) if source else None, params)
500 formats = ["arrow"] if view == "records" else ["xlsx"] if operation in {"excel_write_multiple_sheets", "excel_write_sort"} else ["binary"]
501 outputs[port] = descriptor([view], formats, schema,
502 certainty="known" if schema is not None or view == "bytes" else "unknown")
503 return result(outputs)
504
505 def preview(inputs, params, limits):
506 if operation in collections.FOLDER_OPERATORS or operation in {"excel_parser", "excel_write_multiple_sheets", "excel_write_sort"}:
507 return {}
508 return preview_process(execute, inputs, params, limits)
509
510 run_operator(execute, infer, preview_outputs=preview)