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 piflow_documents as documents
12from xstream_operator import descriptor, preview_process, records_schema, result, run_operator
13
14MAX_INPUT = 8 * 1024 * 1024
15HALF_WIDTH = str.maketrans({**{c: c - 65248 for c in range(0xff01, 0xff5f)}, 0x3000: 32})
16PROVINCES = dict(zip(
17 "beijing tianjin shanghai chongqing anhui fujian gansu guangdong guizhou hainan hebei heilongjiang "
18 "henan hubei hunan jiangsu jiangxi jilin liaoning qinghai shaanxi shanxi shandong sichuan yunnan "
19 "zhejiang inner-mongolia ningxia guangxi xinjiang tibet".split(),
20 "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 "
21 "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(),
22))
23CLEANERS = {"email_clean", "phone_number_clean", "identity_number_clean", "province_clean", "title_clean"}
24SCALERS = {"max_min_normalization", "scope_normalization", "z_score", "discretization"}
25
26
27def clean(value, operation):
28 if value is None:
29 return "" if operation == "province_clean" else None
30 if not isinstance(value, str):
31 raise ValueError("cleaning columns must contain strings")
32 value = value.translate(HALF_WIDTH)
33 if operation == "title_clean":
34 return value
35 if operation == "email_clean":
36 value = value.lower()
37 return value if re.fullmatch(r"[a-z0-9._%+-]+@[a-z0-9.-]+\.[a-z0-9-]+", value) else ""
38 if operation == "phone_number_clean":
39 value = re.sub("[^0-9]", "", value)
40 return value if re.fullmatch(r"1[34578][0-9]{9}", value) else None
41 if operation == "identity_number_clean":
42 value = re.sub("[^0-9X]", "", value.upper()).lstrip("0")
43 if re.fullmatch("[0-9]{15}", value):
44 return value
45 if re.fullmatch("[0-9]{17}[0-9X]", value):
46 weights = (7, 9, 10, 5, 8, 4, 2, 1, 6, 3, 7, 9, 10, 5, 8, 4, 2)
47 checksum = sum(int(digit) * weight for digit, weight in zip(value, weights))
48 if value[-1] == "10X98765432"[checksum % 11]:
49 return value
50 return None
51 normalized = value.strip().casefold().replace(" ", "-")
52 for pinyin, name in PROVINCES.items():
53 if normalized in {pinyin, name.casefold(), name + "省", name + "市"}:
54 return name
55 if name.endswith("自治区") and normalized in {"内蒙古", "宁夏", "广西", "新疆", "西藏"} and name.startswith(normalized):
56 return name
57 return value
58
59
60def names(text):
61 values = [value.strip() for value in text.split(",")]
62 if not all(values) or len(values) != len(set(values)):
63 raise ValueError("column names must be unique and nonempty")
64 return values
65
66
67def field_indices(schema, columns):
68 indices = [schema.get_field_index(name) for name in columns]
69 if -1 in indices:
70 raise ValueError("input includes an unknown or ambiguous column")
71 return indices
72
73
74def scale_columns(operation, params):
75 if operation == "z_score":
76 ins, outs = names(params["inputCols"]), names(params["outputCols"])
77 if len(ins) != len(outs):
78 raise ValueError("inputCols and outputCols must contain the same number of names")
79 return list(zip(ins, outs))
80 return [(params["inputCol"], params["outputCol"])]
81
82
83def scale(values, operation, params):
84 available = [float(value) for value in values if value is not None]
85 if not all(map(math.isfinite, available)):
86 raise ValueError("scaling requires finite numeric input")
87 if not available:
88 return values
89 if operation == "discretization":
90 count = params["numBins"]
91 if not 2 <= count <= 1000:
92 raise ValueError("numBins must be from 2 to 1000")
93 if params["method"] == "EqualWidth":
94 if any(value < 0 or value > count for value in available):
95 raise ValueError("EqualWidth accepts values from zero through numBins")
96 apply = lambda value: min(int(value), count - 1)
97 elif params["method"] == "EqualFrequency":
98 ordered = sorted(available)
99 cuts = sorted({ordered[min(len(ordered) - 1, math.ceil(len(ordered) * i / count) - 1)]
100 for i in range(1, count)} - {ordered[0], ordered[-1]})
101 apply = lambda value: bisect.bisect_right(cuts, value)
102 else:
103 raise ValueError("method must be EqualWidth or EqualFrequency")
104 else:
105 if operation == "z_score":
106 origin = statistics.mean(available)
107 spread = statistics.stdev(available) if len(available) > 1 else 0
108 else:
109 origin = min(available)
110 spread = max(available) - origin
111 low, high = params["range"] if operation == "scope_normalization" else (0, 1)
112 if not math.isfinite(low) or not math.isfinite(high) or low >= high:
113 raise ValueError("range must have two increasing finite bounds")
114 apply = lambda value: (value - origin) / spread * (high - low) + low if spread else None
115 return [None if value is None else apply(value) for value in values]
116
117
118def replace_column(table, name, values):
119 index = table.schema.get_field_index(name)
120 return table.append_column(name, values) if index < 0 else table.set_column(index, name, values)
121
122
123def collect(chunks):
124 data = bytearray()
125 for chunk in chunks:
126 data.extend(chunk)
127 if len(data) > MAX_INPUT:
128 raise ValueError("input exceeds 8 MiB")
129 return bytes(data)
130
131
132def collect_records(port, schema):
133 batches, size, rows = [], 0, 0
134 for batch in port.records():
135 size += batch.nbytes
136 rows += batch.num_rows
137 if size > MAX_INPUT or rows > 100_000:
138 raise ValueError("batch operation accepts at most 8 MiB and 100,000 records")
139 batches.append(batch)
140 return pa.Table.from_batches(batches, schema=schema)
141
142
143def json_rows(data):
144 def invalid_number(value):
145 raise ValueError("non-finite JSON number: " + value)
146
147 root = json.loads(data, parse_constant=invalid_number)
148 rows = root if isinstance(root, list) else [root]
149 if not all(isinstance(row, dict) for row in rows):
150 raise ValueError("JSON input must be an object or an array of objects")
151 # Arrow's Python row inference reads its columns from the first row.
152 columns = dict.fromkeys(key for row in rows for key in row)
153 return pa.table({column: [row.get(column) for row in rows] for column in columns})
154
155
156class XmlBuilder(ElementTree.TreeBuilder):
157 def doctype(self, name, pubid, system):
158 raise ValueError("XML document types are unsupported")
159
160
161def xml_root(data):
162 if len(data) > MAX_INPUT:
163 raise ValueError("XML exceeds 8 MiB")
164 return ElementTree.fromstring(data, parser=ElementTree.XMLParser(target=XmlBuilder()))
165
166
167def xml_rows(root, operation, params):
168 if operation == "xml_parser":
169 selected = list(root.iter(params["rowTag"]))
170 columns = list(dict.fromkeys(child.tag for row in selected for child in row))
171 else:
172 tags = names(params["label"])
173 if root.tag != tags[0] or len(tags) < 2:
174 raise ValueError("label must start with the root and name a repeated child tag")
175 selected = root.findall("/".join(tags[1:]))
176 columns = names(params["schema"])
177 return pa.table({column: pa.array([row.findtext(column) or None for row in selected], type=pa.string())
178 for column in columns})
179
180
181def xml_model(node, depth=0):
182 if depth >= 32:
183 raise ValueError("XML nesting exceeds 32 levels")
184 if not node.attrib and not len(node):
185 return node.text
186 model = {"@" + name: value for name, value in node.attrib.items()}
187 if node.text and node.text.strip():
188 model["#text"] = node.text
189 groups = {}
190 for child in node:
191 groups.setdefault(child.tag, []).append(xml_model(child, depth + 1))
192 model.update({key: values[0] if len(values) == 1 else values for key, values in groups.items()})
193 return model
194
195
196def parse_xml_column(value):
197 if value is None:
198 return None
199 root = xml_root(value)
200 return json.dumps({root.tag: xml_model(root)}, ensure_ascii=False)
201
202
203def put_xml_row(root, row):
204 target = ElementTree.SubElement(root, "ROW")
205 for name, value in row.items():
206 if not re.fullmatch(r"[a-zA-Z_][a-zA-Z0-9_.-]*", name):
207 raise ValueError("record column is not an XML name: " + name)
208 if isinstance(value, (list, dict)):
209 raise ValueError("XML serialization accepts scalar columns")
210 if value is not None:
211 ElementTree.SubElement(target, name).text = str(value)
212
213
214def emit(ctx, table):
215 out = ctx.records_output("result", table.schema)
216 for batch in table.to_batches(max_chunksize=1024):
217 out.write(batch)
218
219
220def inferred_schema(operation, schema, params):
221 if operation in {"docx_parser", "html_parser"}:
222 return documents.RECORDS_TEXT
223 if operation == "pptx_parser":
224 return documents.RECORDS_TEXT.append(pa.field("slide", pa.int64()))
225 if operation == "xml_parser_generate_new_field" and schema is not None:
226 field_indices(schema, [params["decoderField"]])
227 name = params["newField"]
228 if not name or name in schema.names:
229 raise ValueError("newField must be nonempty and absent from the input")
230 return schema.append(pa.field(name, pa.string()))
231 if operation in CLEANERS | {"xml_parser_columns"} and schema is not None:
232 columns = params["xmlColumns"] if operation == "xml_parser_columns" else params["columnName"]
233 indices = field_indices(schema, names(columns))
234 if any(not pa.types.is_string(schema.field(i).type) and not pa.types.is_large_string(schema.field(i).type)
235 for i in indices):
236 raise ValueError("selected columns must be strings")
237 return pa.schema([pa.field(field.name, pa.string()) if i in indices else field
238 for i, field in enumerate(schema)], metadata=schema.metadata)
239 if operation in SCALERS and schema is not None:
240 for source, target in scale_columns(operation, params):
241 field = schema.field(field_indices(schema, [source])[0])
242 if not (pa.types.is_integer(field.type) or pa.types.is_floating(field.type)):
243 raise ValueError("scaling requires integer or floating-point columns")
244 for source, target in scale_columns(operation, params):
245 field = pa.field(target, pa.float64())
246 index = schema.get_field_index(target)
247 schema = schema.append(field) if index == -1 else schema.set(index, field)
248 if operation == "json_string_parser":
249 return json_rows(params["jsonString"]).schema
250 if operation == "xml_string_parser":
251 return pa.schema([(column, pa.string()) for column in names(params["schema"])])
252 return schema if operation in CLEANERS | SCALERS | {"xml_parser_columns"} else None
253
254
255def process(ctx, operation):
256 params = ctx.params
257 if operation in {"json_string_parser", "xml_string_parser"}:
258 if operation == "json_string_parser":
259 emit(ctx, json_rows(params["jsonString"]))
260 else:
261 emit(ctx, xml_rows(xml_root(params["XmlString"]), operation, params))
262 return
263 source = ctx.input("source")
264 if operation in {"docx_parser", "pptx_parser", "html_parser", "flatten_xml_parser", "evaluate_json_path", "decompress_gzip"}:
265 data = collect(source.bytes())
266 if operation == "decompress_gzip":
267 out = ctx.bytes_output("result")
268 for chunk in documents.decompress(data):
269 out.write(chunk)
270 return
271 if operation == "html_parser":
272 table = documents.html_text(data)
273 elif operation in {"docx_parser", "pptx_parser"}:
274 table = documents.office_text(data, operation, xml_root)
275 elif operation == "evaluate_json_path":
276 table = documents.json_field(data, params["tag"], json_rows)
277 else:
278 table = documents.flatten_xml(xml_root(data), params)
279 emit(ctx, table)
280 elif operation == "xml_parser_generate_new_field":
281 schema = inferred_schema(operation, source.schema, params)
282 source_index = schema.get_field_index(params["decoderField"])
283 out = ctx.records_output("result", schema)
284 for batch in source.records():
285 values = [documents.xml_value(value, params["tagXPath"], xml_root)
286 for value in batch.column(source_index).to_pylist()]
287 out.write(pa.RecordBatch.from_arrays([*batch.columns, pa.array(values, type=pa.string())], schema=schema))
288 elif operation in {"json_parser", "xml_parser"}:
289 data = collect(source.bytes())
290 emit(ctx, json_rows(data) if operation == "json_parser" else xml_rows(xml_root(data), operation, params))
291 elif operation == "json_save":
292 out = ctx.bytes_output("result")
293 for batch in source.records():
294 for row in batch.to_pylist():
295 out.write((json.dumps(row, ensure_ascii=False, allow_nan=False) + "\n").encode())
296 elif operation == "xml_save":
297 out = ctx.bytes_output("result")
298 out.write(b"<ROWS>")
299 for batch in source.records():
300 for row in batch.to_pylist():
301 temp = ElementTree.Element("ROWS")
302 put_xml_row(temp, row)
303 out.write(ElementTree.tostring(temp[0], encoding="utf-8"))
304 out.write(b"</ROWS>")
305 elif operation in SCALERS:
306 schema = source.schema
307 inferred_schema(operation, schema, params)
308 original = collect_records(source, schema)
309 table = original
310 for origin, target in scale_columns(operation, params):
311 values = scale(original[origin].to_pylist(), operation, params)
312 table = replace_column(table, target, pa.array(values, type=pa.float64()))
313 emit(ctx, table)
314 else:
315 schema = inferred_schema(operation, source.schema, params)
316 selected = names(params["xmlColumns"] if operation == "xml_parser_columns" else params["columnName"])
317 indices = field_indices(source.schema, selected)
318 out = ctx.records_output("result", schema)
319 for batch in source.records():
320 arrays = list(batch.columns)
321 for index in indices:
322 values = arrays[index].to_pylist()
323 cleaned = (parse_xml_column(value) if operation == "xml_parser_columns" else clean(value, operation)
324 for value in values)
325 arrays[index] = pa.array(cleaned, type=pa.string())
326 out.write(pa.RecordBatch.from_arrays(arrays, schema=schema))
327
328
329def start(operation, output_view):
330 def execute(ctx):
331 process(ctx, operation)
332
333 def infer(inputs, params):
334 schema = None
335 if output_view == "records":
336 source = inputs.get("source")
337 schema = inferred_schema(operation, records_schema(source) if source else None, params)
338 formats = ["arrow"] if output_view == "records" else ["binary"]
339 return result({"result": descriptor([output_view], formats, schema,
340 certainty="known" if schema is not None or output_view == "bytes" else "unknown")})
341
342 def preview(inputs, params, limits):
343 return preview_process(execute, inputs, params, limits)
344
345 run_operator(execute, infer, preview_outputs=preview)