chore: files added

llmpa/fileparser/__init__.py

@@ -1,3 +1,39 @@
 """
 Document file types support
 """
+
+from . import docx
+from . import pdf
+from . import pptx
+from . import xlsx
+from . import csv
+from . import text
+from . import image
+from . import video
+
+from .mimetype import detect
+
+parsers = {
+    "application/pdf": pdf.PdfFileParser,
+    "application/vnd.openxmlformats-officedocument.wordprocessingml.document": docx.DocxFileParser,
+    "application/vnd.openxmlformats-officedocument.presentationml.presentation": pptx.PptxFileParser,
+    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": xlsx.XlsxFileParser,
+    "text/csv": csv.CsvFileParser,
+    "text/plain": text.TextFileParser,
+    "image/gif": image.ImageFileParser,
+    "image/jpeg": image.ImageFileParser,
+    "image/png": image.ImageFileParser,
+    "image/svg+xml": image.ImageFileParser,
+    "video/mp4": video.VideoFileParser,
+    "video/quicktime": video.VideoFileParser,
+    "video/x-msvideo": video.VideoFileParser,
+}
+
+
+def tokenize(filepath: str):
+    mimetype = detect(filepath)
+    if mimetype in parsers:
+        parser = parsers[mimetype](filepath)
+        parser.tokenize()
+    else:
+        print(f"Unsupported file type: {mimetype}")

llmpa/fileparser/__main__.py

@@ -0,0 +1,15 @@
+from . import tokenize
+
+
+def main():
+    import sys
+
+    if len(sys.argv) < 2:
+        print("Usage: document.py <filepath>")
+        sys.exit(1)
+    filepath = sys.argv[1]
+    tokenize(filepath)
+
+
+if __name__ == "__main__":
+    main()

llmpa/fileparser/base.py

@@ -0,0 +1,10 @@
+class BaseFileParser:
+    def __init__(self, file_path):
+        self.file_path = file_path
+        self.file_type = None
+
+    def parse(self):
+        raise NotImplementedError
+
+    def tokenize(self):
+        raise NotImplementedError

llmpa/fileparser/csv.py

@@ -0,0 +1,12 @@
+from .base import BaseFileParser
+
+
+class CsvFileParser(BaseFileParser):
+    def __init__(self, file_path):
+        super().__init__(file_path)
+
+    def parse(self):
+        print("Parsing csv file")
+
+    def tokenize(self):
+        print("Tokenizing csv file")

llmpa/fileparser/docx.py

@@ -0,0 +1,12 @@
+from .base import BaseFileParser
+
+
+class DocxFileParser(BaseFileParser):
+    def __init__(self, file_path):
+        super().__init__(file_path)
+
+    def parse(self):
+        raise NotImplementedError
+
+    def tokenize(self):
+        print("Tokenizing docx file")

llmpa/fileparser/image.py

@@ -0,0 +1,12 @@
+from .base import BaseFileParser
+
+
+class ImageFileParser(BaseFileParser):
+    def __init__(self, file_path):
+        super().__init__(file_path)
+
+    def parse(self):
+        raise NotImplementedError
+
+    def tokenize(self):
+        print("Tokenizing image file")

llmpa/fileparser/pdf.py

@@ -0,0 +1,12 @@
+from .base import BaseFileParser
+
+
+class PdfFileParser(BaseFileParser):
+    def __init__(self, file_path):
+        super().__init__(file_path)
+
+    def parse(self):
+        print("Parsing pdf file")
+
+    def tokenize(self):
+        print("Tokenizing pdf file")

llmpa/fileparser/pptx.py

@@ -0,0 +1,12 @@
+from .base import BaseFileParser
+
+
+class PptxFileParser(BaseFileParser):
+    def __init__(self, file_path):
+        super().__init__(file_path)
+
+    def parse(self):
+        raise NotImplementedError
+
+    def tokenize(self):
+        print("Tokenizing pptx file")

llmpa/fileparser/text.py

@@ -1,7 +1,12 @@
-import common
+from .base import BaseFileParser
 
 
-def tokenize(filepath: str):
-    with open(filepath, "r") as f:
-        text = f.read()
-    return text.split()
+class TextFileParser(BaseFileParser):
+    def __init__(self, file_path):
+        super().__init__(file_path)
+
+    def parse(self):
+        print("Parsing text file")
+
+    def tokenize(self):
+        print("Tokenizing text file")

llmpa/fileparser/video.py

@@ -0,0 +1,12 @@
+from .base import BaseFileParser
+
+
+class VideoFileParser(BaseFileParser):
+    def __init__(self, file_path):
+        super().__init__(file_path)
+
+    def parse(self):
+        print("Parsing video file")
+
+    def tokenize(self):
+        print("Tokenizing video file")

llmpa/fileparser/xlsx.py

@@ -0,0 +1,12 @@
+from .base import BaseFileParser
+
+
+class XlsxFileParser(BaseFileParser):
+    def __init__(self, file_path):
+        super().__init__(file_path)
+
+    def parse(self):
+        raise NotImplementedError
+
+    def tokenize(self):
+        print("Tokenizing xlsx file")