pydatamax 0.1.14__py3-none-any.whl → 0.1.15__py3-none-any.whl

datamax/parser/pptx_parser.py

@@ -1,45 +1,45 @@
-import os
-from typing import Union
-from pptx import Presentation
-from datamax.parser.base import BaseLife
-from datamax.parser.base import MarkdownOutputVo
-
-
-class PPtxParser(BaseLife):
-    def __init__(self, file_path: Union[str, list]):
-        super().__init__()
-        self.file_path = file_path
-
-    @staticmethod
-    def read_ppt_file(file_path: str):
-        try:
-            content = ''
-            prs = Presentation(file_path)
-            for slide in prs.slides:
-                for shape in slide.shapes:
-                    if shape.has_text_frame:
-                        content += shape.text + '\n'
-                    # if shape.shape_type == 13:
-                    #     if not os.path.exists("extracted_images"):
-                    #         os.makedirs("extracted_images")
-                    #     image = shape.image
-                    #     image_filename = f'extracted_images/image_{shape.shape_id}.{image.ext}'
-                    #     with open(image_filename, 'wb') as img_file:
-                    #         img_file.write(image.blob)
-                    #     content += ('[' + image_filename + ']')
-            return content
-        except Exception:
-            raise
-
-    def parse(self, file_path: str) -> MarkdownOutputVo:
-        try:
-            title = self.get_file_extension(file_path)
-            content = self.read_ppt_file(file_path=file_path)
-            mk_content = content
-            lifecycle = self.generate_lifecycle(source_file=file_path, domain="Technology",
-                                                usage_purpose="Documentation", life_type="LLM_ORIGIN")
-            output_vo = MarkdownOutputVo(title, mk_content)
-            output_vo.add_lifecycle(lifecycle)
-            return output_vo.to_dict()
-        except Exception:
-            raise
+import os
+from typing import Union
+from pptx import Presentation
+from datamax.parser.base import BaseLife
+from datamax.parser.base import MarkdownOutputVo
+
+
+class PPtxParser(BaseLife):
+    def __init__(self, file_path: Union[str, list]):
+        super().__init__()
+        self.file_path = file_path
+
+    @staticmethod
+    def read_ppt_file(file_path: str):
+        try:
+            content = ''
+            prs = Presentation(file_path)
+            for slide in prs.slides:
+                for shape in slide.shapes:
+                    if shape.has_text_frame:
+                        content += shape.text + '\n'
+                    # if shape.shape_type == 13:
+                    #     if not os.path.exists("extracted_images"):
+                    #         os.makedirs("extracted_images")
+                    #     image = shape.image
+                    #     image_filename = f'extracted_images/image_{shape.shape_id}.{image.ext}'
+                    #     with open(image_filename, 'wb') as img_file:
+                    #         img_file.write(image.blob)
+                    #     content += ('[' + image_filename + ']')
+            return content
+        except Exception:
+            raise
+
+    def parse(self, file_path: str) -> MarkdownOutputVo:
+        try:
+            title = os.path.splitext(os.path.basename(file_path))[0]
+            content = self.read_ppt_file(file_path=file_path)
+            mk_content = content
+            lifecycle = self.generate_lifecycle(source_file=file_path, domain="Technology",
+                                                usage_purpose="Documentation", life_type="LLM_ORIGIN")
+            output_vo = MarkdownOutputVo(title, mk_content)
+            output_vo.add_lifecycle(lifecycle)
+            return output_vo.to_dict()
+        except Exception:
+            raise

datamax/parser/txt_parser.py

@@ -1,46 +1,46 @@
-import chardet
-from typing import Union
-from datamax.parser.base import BaseLife
-from datamax.parser.base import MarkdownOutputVo
-
-
-class TxtParser(BaseLife):
-    def __init__(self, file_path: Union[str, list]):
-        super().__init__()
-        self.file_path = file_path
-
-    @staticmethod
-    def detect_encoding(file_path: str):
-        try:
-            with open(file_path, 'rb') as f:
-                result = chardet.detect(f.read())
-                return result['encoding']
-        except Exception as e:
-            raise e
-
-    @staticmethod
-    def read_txt_file(file_path: str) -> str:
-        """
-        Reads the Txt file in the specified path and returns its contents.
-        :param file_path: indicates the path of the Txt file to be read.
-        :return: str: Txt file contents.
-        """
-        try:
-            encoding = TxtParser.detect_encoding(file_path)
-            with open(file_path, 'r', encoding=encoding) as file:
-                return file.read()
-        except Exception as e:
-            raise e
-
-    def parse(self, file_path: str) -> MarkdownOutputVo:
-        try:
-            title = self.get_file_extension(file_path)
-            content = self.read_txt_file(file_path=file_path)  # 真实数据是从load加载
-            mk_content = content
-            lifecycle = self.generate_lifecycle(source_file=file_path, domain="Technology",
-                                                usage_purpose="Documentation", life_type="LLM_ORIGIN")
-            output_vo = MarkdownOutputVo(title, mk_content)
-            output_vo.add_lifecycle(lifecycle)
-            return output_vo.to_dict()
-        except Exception as e:
+import chardet
+from typing import Union
+from datamax.parser.base import BaseLife
+from datamax.parser.base import MarkdownOutputVo
+import os
+
+class TxtParser(BaseLife):
+    def __init__(self, file_path: Union[str, list]):
+        super().__init__()
+        self.file_path = file_path
+
+    @staticmethod
+    def detect_encoding(file_path: str):
+        try:
+            with open(file_path, 'rb') as f:
+                result = chardet.detect(f.read())
+                return result['encoding']
+        except Exception as e:
+            raise e
+
+    @staticmethod
+    def read_txt_file(file_path: str) -> str:
+        """
+        Reads the Txt file in the specified path and returns its contents.
+        :param file_path: indicates the path of the Txt file to be read.
+        :return: str: Txt file contents.
+        """
+        try:
+            encoding = TxtParser.detect_encoding(file_path)
+            with open(file_path, 'r', encoding=encoding) as file:
+                return file.read()
+        except Exception as e:
+            raise e
+
+    def parse(self, file_path: str) -> MarkdownOutputVo:
+        try:
+            title = os.path.splitext(os.path.basename(file_path))[0]
+            content = self.read_txt_file(file_path=file_path)  # 真实数据是从load加载
+            mk_content = content
+            lifecycle = self.generate_lifecycle(source_file=file_path, domain="Technology",
+                                                usage_purpose="Documentation", life_type="LLM_ORIGIN")
+            output_vo = MarkdownOutputVo(title, mk_content)
+            output_vo.add_lifecycle(lifecycle)
+            return output_vo.to_dict()
+        except Exception as e:
             raise e

datamax/parser/xls_parser.py

@@ -1,26 +1,26 @@
-from datamax.parser.base import MarkdownOutputVo
-from datamax.parser.base import BaseLife
-import pandas as pd
-import warnings
-
-warnings.filterwarnings("ignore")
-
-
-class XlsParser(BaseLife):
-    """xlsx or xls table use markitdown from Microsoft  so magic for table!"""
-
-    def __init__(self, file_path):
-        super().__init__()
-        self.file_path = file_path
-
-    def parse(self, file_path: str) -> MarkdownOutputVo:
-        try:
-            df = pd.read_excel(file_path)
-            mk_content = df.to_markdown(index=False)
-            lifecycle = self.generate_lifecycle(source_file=file_path, domain="Technology",
-                                                usage_purpose="Documentation", life_type="LLM_ORIGIN")
-            output_vo = MarkdownOutputVo(self.get_file_extension(file_path), mk_content)
-            output_vo.add_lifecycle(lifecycle)
-            return output_vo.to_dict()
-        except Exception as e:
-            raise e
+from datamax.parser.base import MarkdownOutputVo
+from datamax.parser.base import BaseLife
+import pandas as pd
+import warnings
+
+warnings.filterwarnings("ignore")
+
+
+class XlsParser(BaseLife):
+    """xlsx or xls table use markitdown from Microsoft  so magic for table!"""
+
+    def __init__(self, file_path):
+        super().__init__()
+        self.file_path = file_path
+
+    def parse(self, file_path: str) -> MarkdownOutputVo:
+        try:
+            df = pd.read_excel(file_path)
+            mk_content = df.to_markdown(index=False)
+            lifecycle = self.generate_lifecycle(source_file=file_path, domain="Technology",
+                                                usage_purpose="Documentation", life_type="LLM_ORIGIN")
+            output_vo = MarkdownOutputVo(self.get_file_extension(file_path), mk_content)
+            output_vo.add_lifecycle(lifecycle)
+            return output_vo.to_dict()
+        except Exception as e:
+            raise e