upplib 3.4.2__py3-none-any.whl → 3.4.3__py3-none-any.whl

upplib/file_to_text.py

@@ -3,224 +3,6 @@ from upplib.common_package import *
 from upplib.file_function import get_file
 
 
-def to_list(file_name: str = 'a.txt',
-            sep: str = None,
-            sep_line: str = None,
-            sep_line_contain: str = None,
-            sep_line_prefix: str = None,
-            sep_line_suffix: str = None,
-            sep_all: str = None,
-            line_ignore_start_with: list[str] | set[str] | str = None,
-            line_ignore_end_with: list[str] | set[str] | str | None = None,
-            line_ignore_empty: bool | None = None,
-            start_index: int = None,
-            start_line: str = None,
-            end_index: int = None,
-            end_line: str = None,
-            count: int = None,
-            sheet_index: int = 1,
-            column_index: list[str] | set[str] | str | None = None,
-            column_date: list[str] | set[str] | str | None = None,
-            column_datetime: list[str] | set[str] | str | None = None) -> list:
-    """
-    当读取 txt 之类的文件的时候
-    将 txt 文件读取到 list 中, 每一行自动过滤掉行前行后的特殊字符
-    sep             : 是否对每一行进行分割,如果存在这个字段,就分割
-    sep_all         : 将文件转化成一个字符串,然后对这个字符串,再次总体分割
-    start_index     : 从这个地方开始读取,从1开始标号 , 包含这一行
-    start_line      : 从这个地方开始读取,从第一行开始找到这个字符串开始标记 , 包含这一行
-    end_index       : 读取到这个地方结束,从1开始标号 , 不包含这一行
-    end_line        : 读取到这个地方结束,从第一行开始找到这个字符串开始标记 , 不包含这一行
-    count           : 读取指定的行数
-    ##############################################
-    当读取 excel 之类的文件的时候
-    将 excel 文件读取到 list 中, 可以指定 sheet, 也可以指定列 column_index(列) ,自动过滤掉每个单元格前后的特殊字符
-    sheet           : 从 1 开始编号,
-    column_index    : 从 1 开始编号, 指定列
-    column_index    : 如果是指定值, 这个时候返回的是一个 list, 没有嵌套 list
-    column_index    : 如果是 '1,2,3,4'   [1,2,3,4], 返回的是一个嵌套 list[list]
-    column_date     : 指定日期格式的列,规则与 column_index 一样
-    column_datetime : 指定日期格式的列,规则与 column_index 一样
-    返回的数据一定是一个 list
-    """
-    if file_name.endswith('.xls') or file_name.endswith('.xlsx'):
-        return to_list_from_excel(file_name=file_name,
-                                  sheet_index=sheet_index,
-                                  column_index=column_index,
-                                  column_date=column_date,
-                                  column_datetime=column_datetime)
-    return to_list_from_txt(file_name=file_name,
-                            sep=sep,
-                            sep_line=sep_line,
-                            sep_line_contain=sep_line_contain,
-                            sep_line_prefix=sep_line_prefix,
-                            sep_line_suffix=sep_line_suffix,
-                            sep_all=sep_all,
-                            line_ignore_start_with=line_ignore_start_with,
-                            line_ignore_end_with=line_ignore_end_with,
-                            line_ignore_empty=line_ignore_empty,
-                            start_index=start_index,
-                            start_line=start_line,
-                            end_index=end_index,
-                            end_line=end_line,
-                            count=count)
-
-
-def to_list_from_excel(file_name: str = 'a.xls',
-                       sheet_index: int = 1,
-                       column_index: list | int | str | None = None,
-                       column_date: list | int | str | None = None,
-                       column_datetime: list | int | str | None = None) -> list:
-    """
-    当读取 excel 之类的文件的时候
-    将 excel 文件读取到 list 中, 可以指定 sheet, 也可以指定列 column_index(列) ,自动过滤掉每个单元格前后的特殊字符
-    sheet_index     : 从 1 开始编号,
-    column_index    : 从 1 开始编号, 指定列, 如果是指定值是一个, 这个时候返回的是一个 list, 没有嵌套 list
-                       如果是 '1,2,3,4'   [1,2,3,4], 返回的是一个嵌套 list[list]
-    column_date     : 指定日期格式的列,规则与 column_index 一样
-    column_datetime : 指定日期格式的列,规则与 column_index 一样
-    """
-    if file_is_empty(file_name):
-        return []
-    data_list = list()
-    # excel 表格解析成 list 数据
-    list_index = []
-    for one_index in [column_index, column_date, column_datetime]:
-        list_index_one = None
-        if one_index is not None:
-            list_index_one = []
-            if isinstance(one_index, int):
-                list_index_one.append(one_index)
-            if isinstance(one_index, str):
-                i_list = one_index.split(',')
-                for i in i_list:
-                    list_index_one.append(int(i))
-            if isinstance(one_index, list):
-                for i in one_index:
-                    list_index_one.append(int(i))
-        list_index.append(list_index_one)
-    list_all = []
-    for one_list in list_index:
-        if one_list is not None:
-            for o in one_list:
-                list_all.append(o)
-    if len(list_all) > 0 and list_index[0] is not None:
-        list_index[0] = list_all
-    # 是否是单 list 类型的数据
-    list_only_one = False
-    if list_index[0] is not None and len(list_index[0]) == 1:
-        list_only_one = True
-    # 是 xls 格式
-    if file_name.endswith('.xls'):
-        book = xlrd.open_workbook(file_name)  # 打开一个excel
-        sheet = book.sheet_by_index(sheet_index - 1)  # 根据顺序获取sheet
-        for i in range(sheet.nrows):  # 0 1 2 3 4 5
-            rows = sheet.row_values(i)
-            row_data = []
-            for j in range(len(rows)):
-                cell_data = str(rows[j]).strip()
-                is_date = False
-                is_datetime = False
-                # 日期格式的列
-                if list_index[1] is not None and j + 1 in list_index[1]:
-                    cell_data = to_date(xlrd.xldate_as_datetime(to_int(rows[j]), 0))
-                    is_date = True
-                    row_data.append(cell_data)
-                    if list_only_one:
-                        row_data = cell_data
-                # 日期时间格式的列
-                if not is_date and list_index[2] is not None and j + 1 in list_index[2]:
-                    cell_data = to_datetime(xlrd.xldate_as_datetime(to_int(rows[j]), 0))
-                    is_datetime = True
-                    row_data.append(cell_data)
-                    if list_only_one:
-                        row_data = cell_data
-                # 指定需要的列
-                if not is_date and not is_datetime:
-                    if list_index[0] is None:
-                        row_data.append(cell_data)
-                    else:
-                        # 指定需要的列
-                        if j + 1 in list_index[0]:
-                            row_data.append(cell_data)
-                            if list_only_one:
-                                row_data = cell_data
-            data_list.append(row_data)
-    # 是 xlsx 格式
-    if file_name.endswith('.xlsx'):
-        wb = openpyxl.load_workbook(filename=file_name, read_only=True)
-        ws = wb[wb.sheetnames[sheet_index - 1]]
-        for rows in ws.rows:
-            row_data = []
-            for j in range(len(rows)):
-                cell_data = str(rows[j].value).strip()
-                is_date = False
-                is_datetime = False
-                # 日期格式的列
-                if list_index[1] is not None and j + 1 in list_index[1]:
-                    cell_data = to_date(cell_data)
-                    is_date = True
-                    row_data.append(cell_data)
-                    if list_only_one:
-                        row_data = cell_data
-                # 日期时间格式的列
-                if not is_date and list_index[2] is not None and j + 1 in list_index[2]:
-                    cell_data = to_datetime(cell_data)
-                    is_datetime = True
-                    row_data.append(cell_data)
-                    if list_only_one:
-                        row_data = cell_data
-                # 指定需要的列
-                if not is_date and not is_datetime:
-                    if list_index[0] is None:
-                        row_data.append(cell_data)
-                    else:
-                        # 指定需要的列
-                        if j + 1 in list_index[0]:
-                            row_data.append(cell_data)
-                            if list_only_one:
-                                row_data = cell_data
-            data_list.append(row_data)
-    return data_list
-
-
-def to_list_from_txt_with_blank_line(file_name: str = 'a.txt') -> list:
-    """
-    将一个文件中以空行作为分隔符,
-    组成一个 list(list) 数据
-    多行空行,自动合并到一行空行
-    """
-    return to_list_from_txt(file_name, sep_line='')
-
-
-def to_list_json_from_txt(file_name: str = 'a.txt',
-                          start_index: int = None,
-                          start_line: str = None,
-                          start_line_exclude: str | list[str] | set[str] = None,
-                          end_index: int = None,
-                          end_line: str = None,
-                          end_line_exclude: str | list[str] | set[str] = None,
-                          count: int = None) -> list:
-    """
-    将一个文件中的数据按照行来区分,
-    会自动过滤掉空格行,
-    组成一个 list[json] 数据
-    可以将以下文本转 list[json]
-    {"accessKey":"1","signature":"4","timestamp":"1747639787"}
-    {"accessKey":"2","signature":"5","timestamp":"1747639787"}
-    {"accessKey":"3","signature":"6","timestamp":"1747639787"}
-    """
-    return to_list_from_txt(file_name,
-                            start_index=start_index,
-                            start_line=start_line,
-                            start_line_exclude=start_line_exclude,
-                            end_index=end_index,
-                            end_line=end_line,
-                            end_line_exclude=end_line_exclude,
-                            count=count,
-                            line_json=True)
-
-
 def to_list_from_txt(file_name: str = 'a.txt',
                      sep: str = None,
                      sep_line: str = None,
@@ -464,6 +246,224 @@ def to_list_from_txt(file_name: str = 'a.txt',
     return data_list
 
 
+def to_list_from_excel(file_name: str = 'a.xls',
+                       sheet_index: int = 1,
+                       column_index: list | int | str | None = None,
+                       column_date: list | int | str | None = None,
+                       column_datetime: list | int | str | None = None) -> list:
+    """
+    当读取 excel 之类的文件的时候
+    将 excel 文件读取到 list 中, 可以指定 sheet, 也可以指定列 column_index(列) ,自动过滤掉每个单元格前后的特殊字符
+    sheet_index     : 从 1 开始编号,
+    column_index    : 从 1 开始编号, 指定列, 如果是指定值是一个, 这个时候返回的是一个 list, 没有嵌套 list
+                       如果是 '1,2,3,4'   [1,2,3,4], 返回的是一个嵌套 list[list]
+    column_date     : 指定日期格式的列,规则与 column_index 一样
+    column_datetime : 指定日期格式的列,规则与 column_index 一样
+    """
+    if file_is_empty(file_name):
+        return []
+    data_list = list()
+    # excel 表格解析成 list 数据
+    list_index = []
+    for one_index in [column_index, column_date, column_datetime]:
+        list_index_one = None
+        if one_index is not None:
+            list_index_one = []
+            if isinstance(one_index, int):
+                list_index_one.append(one_index)
+            if isinstance(one_index, str):
+                i_list = one_index.split(',')
+                for i in i_list:
+                    list_index_one.append(int(i))
+            if isinstance(one_index, list):
+                for i in one_index:
+                    list_index_one.append(int(i))
+        list_index.append(list_index_one)
+    list_all = []
+    for one_list in list_index:
+        if one_list is not None:
+            for o in one_list:
+                list_all.append(o)
+    if len(list_all) > 0 and list_index[0] is not None:
+        list_index[0] = list_all
+    # 是否是单 list 类型的数据
+    list_only_one = False
+    if list_index[0] is not None and len(list_index[0]) == 1:
+        list_only_one = True
+    # 是 xls 格式
+    if file_name.endswith('.xls'):
+        book = xlrd.open_workbook(file_name)  # 打开一个excel
+        sheet = book.sheet_by_index(sheet_index - 1)  # 根据顺序获取sheet
+        for i in range(sheet.nrows):  # 0 1 2 3 4 5
+            rows = sheet.row_values(i)
+            row_data = []
+            for j in range(len(rows)):
+                cell_data = str(rows[j]).strip()
+                is_date = False
+                is_datetime = False
+                # 日期格式的列
+                if list_index[1] is not None and j + 1 in list_index[1]:
+                    cell_data = to_date(xlrd.xldate_as_datetime(to_int(rows[j]), 0))
+                    is_date = True
+                    row_data.append(cell_data)
+                    if list_only_one:
+                        row_data = cell_data
+                # 日期时间格式的列
+                if not is_date and list_index[2] is not None and j + 1 in list_index[2]:
+                    cell_data = to_datetime(xlrd.xldate_as_datetime(to_int(rows[j]), 0))
+                    is_datetime = True
+                    row_data.append(cell_data)
+                    if list_only_one:
+                        row_data = cell_data
+                # 指定需要的列
+                if not is_date and not is_datetime:
+                    if list_index[0] is None:
+                        row_data.append(cell_data)
+                    else:
+                        # 指定需要的列
+                        if j + 1 in list_index[0]:
+                            row_data.append(cell_data)
+                            if list_only_one:
+                                row_data = cell_data
+            data_list.append(row_data)
+    # 是 xlsx 格式
+    if file_name.endswith('.xlsx'):
+        wb = openpyxl.load_workbook(filename=file_name, read_only=True)
+        ws = wb[wb.sheetnames[sheet_index - 1]]
+        for rows in ws.rows:
+            row_data = []
+            for j in range(len(rows)):
+                cell_data = str(rows[j].value).strip()
+                is_date = False
+                is_datetime = False
+                # 日期格式的列
+                if list_index[1] is not None and j + 1 in list_index[1]:
+                    cell_data = to_date(cell_data)
+                    is_date = True
+                    row_data.append(cell_data)
+                    if list_only_one:
+                        row_data = cell_data
+                # 日期时间格式的列
+                if not is_date and list_index[2] is not None and j + 1 in list_index[2]:
+                    cell_data = to_datetime(cell_data)
+                    is_datetime = True
+                    row_data.append(cell_data)
+                    if list_only_one:
+                        row_data = cell_data
+                # 指定需要的列
+                if not is_date and not is_datetime:
+                    if list_index[0] is None:
+                        row_data.append(cell_data)
+                    else:
+                        # 指定需要的列
+                        if j + 1 in list_index[0]:
+                            row_data.append(cell_data)
+                            if list_only_one:
+                                row_data = cell_data
+            data_list.append(row_data)
+    return data_list
+
+
+def to_list(file_name: str = 'a.txt',
+            sep: str = None,
+            sep_line: str = None,
+            sep_line_contain: str = None,
+            sep_line_prefix: str = None,
+            sep_line_suffix: str = None,
+            sep_all: str = None,
+            line_ignore_start_with: list[str] | set[str] | str = None,
+            line_ignore_end_with: list[str] | set[str] | str | None = None,
+            line_ignore_empty: bool | None = None,
+            start_index: int = None,
+            start_line: str = None,
+            end_index: int = None,
+            end_line: str = None,
+            count: int = None,
+            sheet_index: int = 1,
+            column_index: list[str] | set[str] | str | None = None,
+            column_date: list[str] | set[str] | str | None = None,
+            column_datetime: list[str] | set[str] | str | None = None) -> list:
+    """
+    当读取 txt 之类的文件的时候
+    将 txt 文件读取到 list 中, 每一行自动过滤掉行前行后的特殊字符
+    sep             : 是否对每一行进行分割,如果存在这个字段,就分割
+    sep_all         : 将文件转化成一个字符串,然后对这个字符串,再次总体分割
+    start_index     : 从这个地方开始读取,从1开始标号 , 包含这一行
+    start_line      : 从这个地方开始读取,从第一行开始找到这个字符串开始标记 , 包含这一行
+    end_index       : 读取到这个地方结束,从1开始标号 , 不包含这一行
+    end_line        : 读取到这个地方结束,从第一行开始找到这个字符串开始标记 , 不包含这一行
+    count           : 读取指定的行数
+    ##############################################
+    当读取 excel 之类的文件的时候
+    将 excel 文件读取到 list 中, 可以指定 sheet, 也可以指定列 column_index(列) ,自动过滤掉每个单元格前后的特殊字符
+    sheet           : 从 1 开始编号,
+    column_index    : 从 1 开始编号, 指定列
+    column_index    : 如果是指定值, 这个时候返回的是一个 list, 没有嵌套 list
+    column_index    : 如果是 '1,2,3,4'   [1,2,3,4], 返回的是一个嵌套 list[list]
+    column_date     : 指定日期格式的列,规则与 column_index 一样
+    column_datetime : 指定日期格式的列,规则与 column_index 一样
+    返回的数据一定是一个 list
+    """
+    if file_name.endswith('.xls') or file_name.endswith('.xlsx'):
+        return to_list_from_excel(file_name=file_name,
+                                  sheet_index=sheet_index,
+                                  column_index=column_index,
+                                  column_date=column_date,
+                                  column_datetime=column_datetime)
+    return to_list_from_txt(file_name=file_name,
+                            sep=sep,
+                            sep_line=sep_line,
+                            sep_line_contain=sep_line_contain,
+                            sep_line_prefix=sep_line_prefix,
+                            sep_line_suffix=sep_line_suffix,
+                            sep_all=sep_all,
+                            line_ignore_start_with=line_ignore_start_with,
+                            line_ignore_end_with=line_ignore_end_with,
+                            line_ignore_empty=line_ignore_empty,
+                            start_index=start_index,
+                            start_line=start_line,
+                            end_index=end_index,
+                            end_line=end_line,
+                            count=count)
+
+
+def to_list_from_txt_with_blank_line(file_name: str = 'a.txt') -> list:
+    """
+    将一个文件中以空行作为分隔符,
+    组成一个 list(list) 数据
+    多行空行,自动合并到一行空行
+    """
+    return to_list_from_txt(file_name, sep_line='')
+
+
+def to_list_json_from_txt(file_name: str = 'a.txt',
+                          start_index: int = None,
+                          start_line: str = None,
+                          start_line_exclude: str | list[str] | set[str] = None,
+                          end_index: int = None,
+                          end_line: str = None,
+                          end_line_exclude: str | list[str] | set[str] = None,
+                          count: int = None) -> list:
+    """
+    将一个文件中的数据按照行来区分,
+    会自动过滤掉空格行,
+    组成一个 list[json] 数据
+    可以将以下文本转 list[json]
+    {"accessKey":"1","signature":"4","timestamp":"1747639787"}
+    {"accessKey":"2","signature":"5","timestamp":"1747639787"}
+    {"accessKey":"3","signature":"6","timestamp":"1747639787"}
+    """
+    return to_list_from_txt(file_name,
+                            start_index=start_index,
+                            start_line=start_line,
+                            start_line_exclude=start_line_exclude,
+                            end_index=end_index,
+                            end_line=end_line,
+                            end_line_exclude=end_line_exclude,
+                            count=count,
+                            line_json=True)
+
+
 # 读取文件中的数据,返回一个 str
 def to_str_from_file(file_name: str = 'a.txt',
                      str_join: str = ' ',
@@ -492,13 +492,16 @@ def to_json_from_file(file_name: str = 'a.txt',
                       start_line: str = None,
                       end_index: int = None,
                       end_line: str = None,
+                      line_ignore_start_with=None,
                       count: int = None) -> dict[str, Any]:
+    if line_ignore_start_with is None:
+        line_ignore_start_with = ['//', '/*', '#']
     return to_data_from_file(file_name=file_name,
                              start_index=start_index,
                              start_line=start_line,
                              end_index=end_index,
                              end_line=end_line,
-                             line_ignore_start_with=['//', '/*', '#'],
+                             line_ignore_start_with=line_ignore_start_with,
                              count=count,
                              r_json=True)
 

{upplib-3.4.2.dist-info → upplib-3.4.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: upplib
-Version: 3.4.2
+Version: 3.4.3
 Summary: util
 Author: Luck
 Author-email: wantwaterfish@gmail.com

{upplib-3.4.2.dist-info → upplib-3.4.3.dist-info}/RECORD

@@ -7,7 +7,7 @@ upplib/config_data.py,sha256=KuRh0chqILL-2jXOUngVqjFMzkNZ0QFo_EVpBtptMuc,2757
 upplib/datetime_function.py,sha256=98ro3cV0fvHVoUIHRSv7bvVecBXSrnkqEiP1WhJCwTU,9481
 upplib/db.py,sha256=-3ZALQSzP92-zIhye6ckrXIctbHsVmwoLiCVOlTyDyo,7058
 upplib/file_function.py,sha256=OtVGnmUPd7UO6OJgZjlLgzGMXlftGt94o-_C6-aG2k8,10407
-upplib/file_to_text.py,sha256=P1HHAZDYlJ23jnd0ZU4-JnBDL9l3-bUKjq4kNTXGFH0,26798
+upplib/file_to_text.py,sha256=Qw24mOgwEsOP83P6YVdU1vTvhSH7Xf0HFR5EEi4jGpE,26944
 upplib/format_data.py,sha256=Qxq-OZ8v6HBRJ-tUcNFem1Imbauk3Y5qJTrAGT0CC4I,10153
 upplib/http_util.py,sha256=8Xya5qpeCKGaglxKnirOlOnbnBU3K52FGV5Y9c8HH9k,16119
 upplib/index.py,sha256=hS_luh6lrMvf_RWvZSJk23eFKLHz5BO52fCcwt6QrmA,13833
@@ -19,8 +19,8 @@ upplib/query_log.py,sha256=BAUAVr3lA_GbDzHNjI5beJPs0ngNmy2gCi5Q6UMdr1s,9238
 upplib/redis_tool.py,sha256=I1kOqBwfQWVIOAY-hQaaOn1Zrx8BNlK83u-pk4uHPCA,707
 upplib/text_to_file.py,sha256=a9Fqj1voOZWn2n74IIBjM6CDS62cNyGfB9BRX_m7imo,14918
 upplib/util.py,sha256=K9OAjsbR2R3k0WWPXWWCphxYc25wbPHrW75pweGUSW4,4671
-upplib-3.4.2.dist-info/licenses/LICENSE,sha256=WI5JtXXhjcqnIcPllDA1ZtuxNnZ515xjElcILo7z28o,1073
-upplib-3.4.2.dist-info/METADATA,sha256=wHDVXtMoW0y6TfMruGDquFkPH9mI-ksVyFOD1VMJcyA,940
-upplib-3.4.2.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-upplib-3.4.2.dist-info/top_level.txt,sha256=VwdHDDPP79e1LqtRu5_w30hHB4gT0zlj1weuQYOqFoA,7
-upplib-3.4.2.dist-info/RECORD,,
+upplib-3.4.3.dist-info/licenses/LICENSE,sha256=WI5JtXXhjcqnIcPllDA1ZtuxNnZ515xjElcILo7z28o,1073
+upplib-3.4.3.dist-info/METADATA,sha256=7_Q0nh3FZZOXTQJVcEUJ4mJEvgPFdXEfyZTGoNWVYvw,940
+upplib-3.4.3.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+upplib-3.4.3.dist-info/top_level.txt,sha256=VwdHDDPP79e1LqtRu5_w30hHB4gT0zlj1weuQYOqFoA,7
+upplib-3.4.3.dist-info/RECORD,,