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