upplib 3.4.5__py3-none-any.whl → 3.4.6__py3-none-any.whl

upplib/text_to_text.py

@@ -1,31 +1,86 @@
+from collections import OrderedDict
 from upplib import *
 from upplib.common_package import *
 
 
 def to_list_list(list_data: list[str] = None,
-                 count: int = None) -> list[list[str]]:
+                 count: int = None,
+                 sep_list_word: str = None) -> list[list[str]]:
     """
     将 list 切分成 list(list)
     组成一个 list(list) 数据
     多行空行,自动合并到一行空行
+
+    使用方式:
+    1. 情况1:
+       - 传入 count > 0 时, 按固定数量切分:
+         to_list_list(list_data, 4)
+    2. 情况2:
+       - sep_list_word = 'THIS_LINE_IS_TITLE'
+         不传 count 或 count 为 None/0 时,
+         按行首包含 'THIS_LINE_IS_TITLE' 的标题进行分组:
+         所有相同标题(如 'THIS_LINE_IS_TITLE7.1')及其后内容
+         会被合并到同一个子 list 中, 并按照标题首次出现的顺序返回。
     :param list_data: 原始 list 数据
-    :param count: 每个 list(list) 数据 包含的元素数量
-    :return:
+    :param count: 每个 list(list) 数据 包含的元素数量; 不传则按标题拆分
+    :return: list(list[str])
     """
+    if list_data is None:
+        list_data = []
+
+    # 兼容旧逻辑: 传入 count 时按数量切分
     if count is not None and count > 0:
-        if list_data is None:
-            list_data = []
-        r_list = []
-        o_list = []
+        r_list: list[list[str]] = []
+        o_list: list[str] = []
         c = 0
-        for i in range(len(list_data)):
-            o_list.append(list_data[i])
+        for item in list_data:
+            o_list.append(item)
             c += 1
             if c == count:
                 r_list.append(o_list)
                 o_list = []
                 c = 0
-        if len(o_list):
+        if o_list:
             r_list.append(o_list)
         return r_list
+
+    # 新逻辑: 按标题拆分
+    # 期望输入示例:
+    #   阿斯顿发sas地方0
+    #   THIS_LINE_IS_TITLE7.1 （重点）技术创新含义、分
+    #   阿斯顿发地方1
+    #   ...
+    #   THIS_LINE_IS_TITLE7.2 （重点）技术创新含义、分
+    #   阿斯顿发地方111
+    #   ...
+    #
+    # 输出示例(概念上):
+    #   [
+    #       [所有与 THIS_LINE_IS_TITLE7.1 相关的行...],
+    #       [所有与 THIS_LINE_IS_TITLE7.2 相关的行...]
+    #   ]
+    if sep_list_word is not None:
+        groups: "OrderedDict[str, list[str]]" = OrderedDict()
+        current_key: str | None = None
+        for line in list_data:
+            if not isinstance(line, str):
+                # 非字符串, 直接跳过
+                continue
+            # 识别标题行: 以 THIS_LINE_IS_TITLE 开头
+            stripped = line.strip()
+            if stripped.startswith(sep_list_word):
+                # 取到第一个空格之前作为分组 key:
+                # "THIS_LINE_IS_TITLE7.2 （重点）技术创新含义、分"
+                # -> "THIS_LINE_IS_TITLE7.2"
+                first_part = "".join([c for c in stripped if c.isdigit()])
+                current_key = first_part
+                if current_key not in groups:
+                    groups[current_key] = []
+                groups[current_key].append(line)
+            else:
+                # 非标题行, 如果已经有当前标题, 归到当前标题下;
+                # 若还未遇到任何标题(例如开头的杂项行), 直接忽略
+                if current_key is not None:
+                    groups[current_key].append(line)
+        return list(groups.values())
     return []

{upplib-3.4.5.dist-info → upplib-3.4.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: upplib
-Version: 3.4.5
+Version: 3.4.6
 Summary: util
 Author: Luck
 Author-email: wantwaterfish@gmail.com

{upplib-3.4.5.dist-info → upplib-3.4.6.dist-info}/RECORD

@@ -18,10 +18,10 @@ upplib/multi_thread.py,sha256=zOeWG5HGYIzwqiPvef-4ak5bzorf0S3q6Ht8wPit_M0,2705
 upplib/query_log.py,sha256=BAUAVr3lA_GbDzHNjI5beJPs0ngNmy2gCi5Q6UMdr1s,9238
 upplib/redis_tool.py,sha256=I1kOqBwfQWVIOAY-hQaaOn1Zrx8BNlK83u-pk4uHPCA,707
 upplib/text_to_file.py,sha256=6EMfq9yB5FXSijKNetVSH83bhb0Ipzpu6QIoSwOONHQ,14876
-upplib/text_to_text.py,sha256=T4vvl_QF5s5-m87gzyvggUtXU1gJn7_4DNAarTAyKEI,869
+upplib/text_to_text.py,sha256=yG-uasz48mFTY0s7Nyu6_HZ2VXD8e1Nwezoeax2naMI,3194
 upplib/util.py,sha256=K9OAjsbR2R3k0WWPXWWCphxYc25wbPHrW75pweGUSW4,4671
-upplib-3.4.5.dist-info/licenses/LICENSE,sha256=WI5JtXXhjcqnIcPllDA1ZtuxNnZ515xjElcILo7z28o,1073
-upplib-3.4.5.dist-info/METADATA,sha256=1Gd6lmOuSWsYhWx5FtESyhoefqiEn6q20YRFKQqacSM,940
-upplib-3.4.5.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-upplib-3.4.5.dist-info/top_level.txt,sha256=VwdHDDPP79e1LqtRu5_w30hHB4gT0zlj1weuQYOqFoA,7
-upplib-3.4.5.dist-info/RECORD,,
+upplib-3.4.6.dist-info/licenses/LICENSE,sha256=WI5JtXXhjcqnIcPllDA1ZtuxNnZ515xjElcILo7z28o,1073
+upplib-3.4.6.dist-info/METADATA,sha256=TE6rmys6H5ZKib_qnY6Ei9pyBIyf5fJ57_gSUuhxk7g,940
+upplib-3.4.6.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+upplib-3.4.6.dist-info/top_level.txt,sha256=VwdHDDPP79e1LqtRu5_w30hHB4gT0zlj1weuQYOqFoA,7
+upplib-3.4.6.dist-info/RECORD,,