sophhub 0.4.19 → 0.4.21

package/skills/sophnet-customer-management/src/src/customer_mgmt_core/exporter.py

@@ -1,85 +1,85 @@
-from __future__ import annotations
-
-import csv
-import json
-from pathlib import Path
-from typing import Any
-
-import openpyxl
-
-
-def flatten_customers(customers: list[dict[str, Any]]) -> list[dict[str, Any]]:
-    rows: list[dict[str, Any]] = []
-    for customer in customers:
-        row = {
-            "客户ID": customer["customer_id"],
-            "姓名": customer.get("name"),
-            "手机号": customer.get("primary_phone"),
-            "生日": customer.get("birthday"),
-            "标签": "，".join(customer.get("tags", [])),
-            "备注": customer.get("notes"),
-            "最近更新时间": customer.get("updated_at"),
-        }
-        for field_key, item in customer.get("dynamic_field_map", {}).items():
-            row[item.get("label") or field_key] = item.get("displayValue") or item.get("value")
-        rows.append(row)
-    return rows
-
-
-def export_customers(customers: list[dict[str, Any]], output_path: str | Path) -> dict[str, Any]:
-    path = Path(output_path)
-    path.parent.mkdir(parents=True, exist_ok=True)
-    rows = flatten_customers(customers)
-    if path.suffix.lower() == ".csv":
-        _write_csv(rows, path)
-    elif path.suffix.lower() == ".xlsx":
-        _write_xlsx(rows, path)
-    elif path.suffix.lower() == ".json":
-        path.write_text(json.dumps(rows, ensure_ascii=False, indent=2), encoding="utf-8")
-    else:
-        raise ValueError("仅支持导出为 .csv / .xlsx / .json")
-    return {"output_path": str(path), "row_count": len(rows)}
-
-
-def preview_as_markdown(customers: list[dict[str, Any]], limit: int = 20) -> str:
-    rows = flatten_customers(customers)[:limit]
-    if not rows:
-        return "暂无客户数据。"
-    headers = list(rows[0].keys())
-    lines = [
-        "| " + " | ".join(headers) + " |",
-        "| " + " | ".join(["---"] * len(headers)) + " |",
-    ]
-    for row in rows:
-        lines.append("| " + " | ".join(str(row.get(header, "") or "") for header in headers) + " |")
-    return "\n".join(lines)
-
-
-def _write_csv(rows: list[dict[str, Any]], path: Path) -> None:
-    headers = _collect_headers(rows)
-    with path.open("w", encoding="utf-8-sig", newline="") as file:
-        writer = csv.DictWriter(file, fieldnames=headers)
-        writer.writeheader()
-        writer.writerows(rows)
-
-
-def _write_xlsx(rows: list[dict[str, Any]], path: Path) -> None:
-    workbook = openpyxl.Workbook()
-    sheet = workbook.active
-    sheet.title = "客户数据"
-    headers = _collect_headers(rows)
-    sheet.append(headers)
-    for row in rows:
-        sheet.append([row.get(header, "") for header in headers])
-    workbook.save(path)
-
-
-def _collect_headers(rows: list[dict[str, Any]]) -> list[str]:
-    headers: list[str] = []
-    seen: set[str] = set()
-    for row in rows:
-        for key in row.keys():
-            if key not in seen:
-                seen.add(key)
-                headers.append(key)
-    return headers
+from __future__ import annotations
+
+import csv
+import json
+from pathlib import Path
+from typing import Any
+
+import openpyxl
+
+
+def flatten_customers(customers: list[dict[str, Any]]) -> list[dict[str, Any]]:
+    rows: list[dict[str, Any]] = []
+    for customer in customers:
+        row = {
+            "客户ID": customer["customer_id"],
+            "姓名": customer.get("name"),
+            "手机号": customer.get("primary_phone"),
+            "生日": customer.get("birthday"),
+            "标签": "，".join(customer.get("tags", [])),
+            "备注": customer.get("notes"),
+            "最近更新时间": customer.get("updated_at"),
+        }
+        for field_key, item in customer.get("dynamic_field_map", {}).items():
+            row[item.get("label") or field_key] = item.get("displayValue") or item.get("value")
+        rows.append(row)
+    return rows
+
+
+def export_customers(customers: list[dict[str, Any]], output_path: str | Path) -> dict[str, Any]:
+    path = Path(output_path)
+    path.parent.mkdir(parents=True, exist_ok=True)
+    rows = flatten_customers(customers)
+    if path.suffix.lower() == ".csv":
+        _write_csv(rows, path)
+    elif path.suffix.lower() == ".xlsx":
+        _write_xlsx(rows, path)
+    elif path.suffix.lower() == ".json":
+        path.write_text(json.dumps(rows, ensure_ascii=False, indent=2), encoding="utf-8")
+    else:
+        raise ValueError("仅支持导出为 .csv / .xlsx / .json")
+    return {"output_path": str(path), "row_count": len(rows)}
+
+
+def preview_as_markdown(customers: list[dict[str, Any]], limit: int = 20) -> str:
+    rows = flatten_customers(customers)[:limit]
+    if not rows:
+        return "暂无客户数据。"
+    headers = list(rows[0].keys())
+    lines = [
+        "| " + " | ".join(headers) + " |",
+        "| " + " | ".join(["---"] * len(headers)) + " |",
+    ]
+    for row in rows:
+        lines.append("| " + " | ".join(str(row.get(header, "") or "") for header in headers) + " |")
+    return "\n".join(lines)
+
+
+def _write_csv(rows: list[dict[str, Any]], path: Path) -> None:
+    headers = _collect_headers(rows)
+    with path.open("w", encoding="utf-8-sig", newline="") as file:
+        writer = csv.DictWriter(file, fieldnames=headers)
+        writer.writeheader()
+        writer.writerows(rows)
+
+
+def _write_xlsx(rows: list[dict[str, Any]], path: Path) -> None:
+    workbook = openpyxl.Workbook()
+    sheet = workbook.active
+    sheet.title = "客户数据"
+    headers = _collect_headers(rows)
+    sheet.append(headers)
+    for row in rows:
+        sheet.append([row.get(header, "") for header in headers])
+    workbook.save(path)
+
+
+def _collect_headers(rows: list[dict[str, Any]]) -> list[str]:
+    headers: list[str] = []
+    seen: set[str] = set()
+    for row in rows:
+        for key in row.keys():
+            if key not in seen:
+                seen.add(key)
+                headers.append(key)
+    return headers

package/skills/sophnet-customer-management/src/src/customer_mgmt_core/models.py

@@ -1,84 +1,84 @@
-from __future__ import annotations
-
-from dataclasses import asdict, dataclass, field
-from typing import Any
-
-
-BUILTIN_CUSTOMER_FIELDS = {
-    "name",
-    "primary_phone",
-    "birthday",
-    "tags",
-    "notes",
-}
-
-
-@dataclass(slots=True)
-class FieldDefinition:
-    field_key: str
-    label: str
-    value_type: str = "string"
-    entity_type: str = "customer"
-    is_required: bool = False
-    source: str = "user_confirmed"
-    status: str = "active"
-    aliases: list[str] = field(default_factory=list)
-
-    def to_dict(self) -> dict[str, Any]:
-        return asdict(self)
-
-
-@dataclass(slots=True)
-class CustomerPayload:
-    name: str
-    primary_phone: str | None = None
-    birthday: str | None = None
-    tags: list[str] = field(default_factory=list)
-    notes: str | None = None
-    dynamic_fields: dict[str, Any] = field(default_factory=dict)
-
-    def to_dict(self) -> dict[str, Any]:
-        return asdict(self)
-
-
-@dataclass(slots=True)
-class BusinessRecordPayload:
-    customer_id: str
-    record_type: str
-    status: str | None = None
-    record_date: str | None = None
-    amount: str | None = None
-    title: str | None = None
-    raw_payload: dict[str, Any] = field(default_factory=dict)
-
-    def to_dict(self) -> dict[str, Any]:
-        return asdict(self)
-
-
-@dataclass(slots=True)
-class ReminderPlan:
-    customer_id: str
-    customer_name: str
-    reminder_type: str
-    title: str
-    trigger_at: str | None
-    cron_expr: str
-    message: str
-    recurring: bool = False
-
-    def to_dict(self) -> dict[str, Any]:
-        return asdict(self)
-
-
-@dataclass(slots=True)
-class ImportPreview:
-    mode: str
-    source_file: str
-    customer_count: int
-    record_count: int
-    new_field_count: int
-    warnings: list[str] = field(default_factory=list)
-    preview_rows: list[dict[str, Any]] = field(default_factory=list)
-
-    def to_dict(self) -> dict[str, Any]:
-        return asdict(self)
+from __future__ import annotations
+
+from dataclasses import asdict, dataclass, field
+from typing import Any
+
+
+BUILTIN_CUSTOMER_FIELDS = {
+    "name",
+    "primary_phone",
+    "birthday",
+    "tags",
+    "notes",
+}
+
+
+@dataclass(slots=True)
+class FieldDefinition:
+    field_key: str
+    label: str
+    value_type: str = "string"
+    entity_type: str = "customer"
+    is_required: bool = False
+    source: str = "user_confirmed"
+    status: str = "active"
+    aliases: list[str] = field(default_factory=list)
+
+    def to_dict(self) -> dict[str, Any]:
+        return asdict(self)
+
+
+@dataclass(slots=True)
+class CustomerPayload:
+    name: str
+    primary_phone: str | None = None
+    birthday: str | None = None
+    tags: list[str] = field(default_factory=list)
+    notes: str | None = None
+    dynamic_fields: dict[str, Any] = field(default_factory=dict)
+
+    def to_dict(self) -> dict[str, Any]:
+        return asdict(self)
+
+
+@dataclass(slots=True)
+class BusinessRecordPayload:
+    customer_id: str
+    record_type: str
+    status: str | None = None
+    record_date: str | None = None
+    amount: str | None = None
+    title: str | None = None
+    raw_payload: dict[str, Any] = field(default_factory=dict)
+
+    def to_dict(self) -> dict[str, Any]:
+        return asdict(self)
+
+
+@dataclass(slots=True)
+class ReminderPlan:
+    customer_id: str
+    customer_name: str
+    reminder_type: str
+    title: str
+    trigger_at: str | None
+    cron_expr: str
+    message: str
+    recurring: bool = False
+
+    def to_dict(self) -> dict[str, Any]:
+        return asdict(self)
+
+
+@dataclass(slots=True)
+class ImportPreview:
+    mode: str
+    source_file: str
+    customer_count: int
+    record_count: int
+    new_field_count: int
+    warnings: list[str] = field(default_factory=list)
+    preview_rows: list[dict[str, Any]] = field(default_factory=list)
+
+    def to_dict(self) -> dict[str, Any]:
+        return asdict(self)

package/skills/sophnet-customer-management/src/src/customer_mgmt_core/normalizer.py

@@ -1,144 +1,144 @@
-from __future__ import annotations
-
-import hashlib
-import json
-import re
-from datetime import date, datetime
-from typing import Any
-
-
-NULL_MARKERS = {"", "nan", "none", "null", "nat", "未填写", "暂无", "-"}
-
-
-def clean_text(value: Any) -> str:
-    if value is None:
-        return ""
-    text = str(value).strip()
-    text = text.replace("\u3000", " ")
-    text = re.sub(r"\s+", " ", text)
-    return text
-
-
-def is_blank(value: Any) -> bool:
-    return clean_text(value).lower() in NULL_MARKERS
-
-
-def normalize_optional_text(value: Any) -> str | None:
-    text = clean_text(value)
-    if text.lower() in NULL_MARKERS:
-        return None
-    return text
-
-
-def normalize_phone(value: Any) -> str | None:
-    text = clean_text(value)
-    if not text:
-        return None
-    digits = re.sub(r"\D+", "", text)
-    if len(digits) >= 11:
-        return digits[-11:]
-    if len(digits) >= 7:
-        return digits
-    return None
-
-
-def normalize_date(value: Any) -> str | None:
-    text = clean_text(value)
-    if not text or text.lower() in NULL_MARKERS:
-        return None
-    text = text.replace("年", ".").replace("月", ".").replace("日", "")
-    text = text.replace("/", ".").replace("-", ".")
-    text = re.sub(r"\.+", ".", text).strip(".")
-    candidates = [
-        "%Y.%m.%d",
-        "%Y.%m",
-        "%m.%d",
-    ]
-    for fmt in candidates:
-        try:
-            parsed = datetime.strptime(text, fmt)
-            year = parsed.year
-            if fmt == "%m.%d":
-                year = date.today().year
-            month = parsed.month
-            day = parsed.day if "%d" in fmt else 1
-            return date(year, month, day).isoformat()
-        except ValueError:
-            continue
-    if re.fullmatch(r"\d{4}\.\d{1,2}\.\d{1,2}", text):
-        parts = [int(item) for item in text.split(".")]
-        return date(parts[0], parts[1], parts[2]).isoformat()
-    return None
-
-
-def normalize_tags(value: Any) -> list[str]:
-    if isinstance(value, (list, tuple, set)):
-        return [clean_text(item) for item in value if clean_text(item)]
-    text = clean_text(value)
-    if not text:
-        return []
-    parts = re.split(r"[,，、/\s]+", text)
-    return [item for item in (part.strip() for part in parts) if item]
-
-
-def normalize_money(value: Any) -> str | None:
-    text = clean_text(value)
-    if not text or text.lower() in NULL_MARKERS:
-        return None
-    return text
-
-
-def normalize_value_for_type(value: Any, value_type: str) -> str | None:
-    if value_type == "date":
-        return normalize_date(value)
-    if value_type == "phone":
-        return normalize_phone(value)
-    if value_type == "tags":
-        tags = normalize_tags(value)
-        return json.dumps(tags, ensure_ascii=False)
-    if value_type == "money":
-        return normalize_money(value)
-    return normalize_optional_text(value)
-
-
-def guess_value_type(label: str, values: list[Any]) -> str:
-    joined_label = clean_text(label).lower()
-    if any(keyword in joined_label for keyword in ["微信", "wechat", "wx"]):
-        return "string"
-    if any(keyword in joined_label for keyword in ["电话", "手机", "手机号", "mobile", "phone"]):
-        return "phone"
-    if any(keyword in joined_label for keyword in ["生日", "日期", "时间", "生效", "到期", "续费", "回访", "预约"]):
-        return "date"
-    if any(keyword in joined_label for keyword in ["金额", "保费", "保额", "消费", "价格", "佣金"]):
-        return "money"
-
-    non_blank = [clean_text(value) for value in values if not is_blank(value)]
-    if not non_blank:
-        return "string"
-
-    date_hits = sum(1 for value in non_blank if normalize_date(value))
-    if date_hits == len(non_blank):
-        return "date"
-
-    phone_hits = sum(1 for value in non_blank if normalize_phone(value))
-    if phone_hits == len(non_blank):
-        return "phone"
-
-    numeric_hits = sum(1 for value in non_blank if re.fullmatch(r"[\d.]+", value))
-    if numeric_hits == len(non_blank):
-        return "number"
-
-    return "string"
-
-
-def stable_field_key(label: str) -> str:
-    text = clean_text(label).lower()
-    ascii_text = re.sub(r"[^a-z0-9]+", "_", text).strip("_")
-    if ascii_text:
-        return ascii_text[:48]
-    digest = hashlib.sha1(clean_text(label).encode("utf-8")).hexdigest()[:12]
-    return f"fld_{digest}"
-
-
-def dumps_json(data: Any) -> str:
-    return json.dumps(data, ensure_ascii=False, sort_keys=True)
+from __future__ import annotations
+
+import hashlib
+import json
+import re
+from datetime import date, datetime
+from typing import Any
+
+
+NULL_MARKERS = {"", "nan", "none", "null", "nat", "未填写", "暂无", "-"}
+
+
+def clean_text(value: Any) -> str:
+    if value is None:
+        return ""
+    text = str(value).strip()
+    text = text.replace("\u3000", " ")
+    text = re.sub(r"\s+", " ", text)
+    return text
+
+
+def is_blank(value: Any) -> bool:
+    return clean_text(value).lower() in NULL_MARKERS
+
+
+def normalize_optional_text(value: Any) -> str | None:
+    text = clean_text(value)
+    if text.lower() in NULL_MARKERS:
+        return None
+    return text
+
+
+def normalize_phone(value: Any) -> str | None:
+    text = clean_text(value)
+    if not text:
+        return None
+    digits = re.sub(r"\D+", "", text)
+    if len(digits) >= 11:
+        return digits[-11:]
+    if len(digits) >= 7:
+        return digits
+    return None
+
+
+def normalize_date(value: Any) -> str | None:
+    text = clean_text(value)
+    if not text or text.lower() in NULL_MARKERS:
+        return None
+    text = text.replace("年", ".").replace("月", ".").replace("日", "")
+    text = text.replace("/", ".").replace("-", ".")
+    text = re.sub(r"\.+", ".", text).strip(".")
+    candidates = [
+        "%Y.%m.%d",
+        "%Y.%m",
+        "%m.%d",
+    ]
+    for fmt in candidates:
+        try:
+            parsed = datetime.strptime(text, fmt)
+            year = parsed.year
+            if fmt == "%m.%d":
+                year = date.today().year
+            month = parsed.month
+            day = parsed.day if "%d" in fmt else 1
+            return date(year, month, day).isoformat()
+        except ValueError:
+            continue
+    if re.fullmatch(r"\d{4}\.\d{1,2}\.\d{1,2}", text):
+        parts = [int(item) for item in text.split(".")]
+        return date(parts[0], parts[1], parts[2]).isoformat()
+    return None
+
+
+def normalize_tags(value: Any) -> list[str]:
+    if isinstance(value, (list, tuple, set)):
+        return [clean_text(item) for item in value if clean_text(item)]
+    text = clean_text(value)
+    if not text:
+        return []
+    parts = re.split(r"[,，、/\s]+", text)
+    return [item for item in (part.strip() for part in parts) if item]
+
+
+def normalize_money(value: Any) -> str | None:
+    text = clean_text(value)
+    if not text or text.lower() in NULL_MARKERS:
+        return None
+    return text
+
+
+def normalize_value_for_type(value: Any, value_type: str) -> str | None:
+    if value_type == "date":
+        return normalize_date(value)
+    if value_type == "phone":
+        return normalize_phone(value)
+    if value_type == "tags":
+        tags = normalize_tags(value)
+        return json.dumps(tags, ensure_ascii=False)
+    if value_type == "money":
+        return normalize_money(value)
+    return normalize_optional_text(value)
+
+
+def guess_value_type(label: str, values: list[Any]) -> str:
+    joined_label = clean_text(label).lower()
+    if any(keyword in joined_label for keyword in ["微信", "wechat", "wx"]):
+        return "string"
+    if any(keyword in joined_label for keyword in ["电话", "手机", "手机号", "mobile", "phone"]):
+        return "phone"
+    if any(keyword in joined_label for keyword in ["生日", "日期", "时间", "生效", "到期", "续费", "回访", "预约"]):
+        return "date"
+    if any(keyword in joined_label for keyword in ["金额", "保费", "保额", "消费", "价格", "佣金"]):
+        return "money"
+
+    non_blank = [clean_text(value) for value in values if not is_blank(value)]
+    if not non_blank:
+        return "string"
+
+    date_hits = sum(1 for value in non_blank if normalize_date(value))
+    if date_hits == len(non_blank):
+        return "date"
+
+    phone_hits = sum(1 for value in non_blank if normalize_phone(value))
+    if phone_hits == len(non_blank):
+        return "phone"
+
+    numeric_hits = sum(1 for value in non_blank if re.fullmatch(r"[\d.]+", value))
+    if numeric_hits == len(non_blank):
+        return "number"
+
+    return "string"
+
+
+def stable_field_key(label: str) -> str:
+    text = clean_text(label).lower()
+    ascii_text = re.sub(r"[^a-z0-9]+", "_", text).strip("_")
+    if ascii_text:
+        return ascii_text[:48]
+    digest = hashlib.sha1(clean_text(label).encode("utf-8")).hexdigest()[:12]
+    return f"fld_{digest}"
+
+
+def dumps_json(data: Any) -> str:
+    return json.dumps(data, ensure_ascii=False, sort_keys=True)