pembot 0.1.3__tar.gz → 0.1.5__tar.gz

{pembot-0.1.3 → pembot-0.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pembot
-Version: 0.1.3
+Version: 0.1.5
 Summary: A Python Package to convert PEM blog content to usseful information by leveraging LLMs
 Author-email: cyto <aryan_sidhwani@protonmail.com>
 License-Expression: MIT

pembot-0.1.5/pembot/.git/COMMIT_EDITMSG

@@ -0,0 +1 @@
+cyto/fixed a file already open error and wrote to file if myfile is excel type and output_dir is given

{pembot-0.1.3 → pembot-0.1.5}/pembot/.git/logs/HEAD

@@ -15,3 +15,5 @@ a898d2c3947d30d8be64bd2bbcef68f956d5456b 784aa28d912b66e07748483efe0326c70d7541a
 f214d4d56726e2928479c5948bd88e038cf70b2e 8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a cyto <silverstone965@gmail.com> 1752859643 +0530	commit: minor oopsie
 8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a 203b390ad0aeb3bc5a8540840b004e6a42e5ce7a cyto <silverstone965@gmail.com> 1752865439 +0530	commit: added requirements
 203b390ad0aeb3bc5a8540840b004e6a42e5ce7a c3cc0da3d955ecec0f865c46c030a0c073697495 cyto <silverstone965@gmail.com> 1758877816 +0530	commit: cyto/fixed the excel to markdown conversion
+c3cc0da3d955ecec0f865c46c030a0c073697495 e6adbc3c373070269f97ef82d4f63027d7878f67 cyto <silverstone965@gmail.com> 1758880975 +0530	commit: cyto/put the output of the converted file in excel case to write to file if path is given
+e6adbc3c373070269f97ef82d4f63027d7878f67 81d01e1c63d48b096c77aae83471d42272ca9fce cyto <silverstone965@gmail.com> 1758890262 +0530	commit: cyto/fixed a file already open error and wrote to file if myfile is excel type and output_dir is given

{pembot-0.1.3 → pembot-0.1.5}/pembot/.git/logs/refs/heads/main

@@ -15,3 +15,5 @@ a898d2c3947d30d8be64bd2bbcef68f956d5456b 784aa28d912b66e07748483efe0326c70d7541a
 f214d4d56726e2928479c5948bd88e038cf70b2e 8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a cyto <silverstone965@gmail.com> 1752859643 +0530	commit: minor oopsie
 8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a 203b390ad0aeb3bc5a8540840b004e6a42e5ce7a cyto <silverstone965@gmail.com> 1752865439 +0530	commit: added requirements
 203b390ad0aeb3bc5a8540840b004e6a42e5ce7a c3cc0da3d955ecec0f865c46c030a0c073697495 cyto <silverstone965@gmail.com> 1758877816 +0530	commit: cyto/fixed the excel to markdown conversion
+c3cc0da3d955ecec0f865c46c030a0c073697495 e6adbc3c373070269f97ef82d4f63027d7878f67 cyto <silverstone965@gmail.com> 1758880975 +0530	commit: cyto/put the output of the converted file in excel case to write to file if path is given
+e6adbc3c373070269f97ef82d4f63027d7878f67 81d01e1c63d48b096c77aae83471d42272ca9fce cyto <silverstone965@gmail.com> 1758890262 +0530	commit: cyto/fixed a file already open error and wrote to file if myfile is excel type and output_dir is given

{pembot-0.1.3 → pembot-0.1.5}/pembot/.git/logs/refs/remotes/origin/main

@@ -14,3 +14,5 @@ a898d2c3947d30d8be64bd2bbcef68f956d5456b 784aa28d912b66e07748483efe0326c70d7541a
 f214d4d56726e2928479c5948bd88e038cf70b2e 8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a cyto <silverstone965@gmail.com> 1752859659 +0530	update by push
 8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a 203b390ad0aeb3bc5a8540840b004e6a42e5ce7a cyto <silverstone965@gmail.com> 1752865472 +0530	update by push
 203b390ad0aeb3bc5a8540840b004e6a42e5ce7a c3cc0da3d955ecec0f865c46c030a0c073697495 cyto <silverstone965@gmail.com> 1758877832 +0530	update by push
+c3cc0da3d955ecec0f865c46c030a0c073697495 e6adbc3c373070269f97ef82d4f63027d7878f67 cyto <silverstone965@gmail.com> 1758880990 +0530	update by push
+e6adbc3c373070269f97ef82d4f63027d7878f67 81d01e1c63d48b096c77aae83471d42272ca9fce cyto <silverstone965@gmail.com> 1758890281 +0530	update by push

pembot-0.1.5/pembot/.git/objects/00/3ba85af0ed7b9f6ab099ca298c3d0c18fb002b

@@ -0,0 +1 @@
+x
e��� E����.Mc�����M�Cͣb��@���.���{�v��ж;)�8C���q�p$���b��ҁv<nA���nN������c�e�WpT8�0���%���*Y*�Rp�jߴͱ&��ƣ

pembot-0.1.5/pembot/.git/objects/05/5e82e69847a636258cb994bb920c03a93b5ff4

@@ -0,0 +1 @@
+x
+)JMU0�d040031Q�����,���+�dx6���M�9{wk�+��q�IO�D������Ԣ��"�:��5:f�x1a�]�`ܱ;�3L
�M#�

pembot-0.1.5/pembot/.git/objects/81/d01e1c63d48b096c77aae83471d42272ca9fce

@@ -0,0 +1,2 @@
+x
��[n� E��U���@`@����1�H�Xx�Ļ/mwп���8��saPg��	(ɻl�6I�D�ƀQS���t���;-d|
+QE�J���e���L�l���Т�'��W�np�J�S߸-���;����w8��֍!	��$��@�T����\���C.���N>�VZ�zD~I��	�o�d��?�
=#U�c�l;�;�ҡlp+wZ�o�tgT

pembot-0.1.5/pembot/.git/objects/e6/adbc3c373070269f97ef82d4f63027d7878f67

@@ -0,0 +1 @@
+x
��Kn�@D���GJ��#��\�c��Ш1���a&7Ȯ>*Փ�,��!�XUT

pembot-0.1.5/pembot/.git/refs/heads/main

@@ -0,0 +1 @@
+81d01e1c63d48b096c77aae83471d42272ca9fce

pembot-0.1.5/pembot/.git/refs/remotes/origin/main

@@ -0,0 +1 @@
+81d01e1c63d48b096c77aae83471d42272ca9fce

{pembot-0.1.3 → pembot-0.1.5}/pembot/AnyToText/convertor.py

@@ -40,20 +40,21 @@ class Convertor():
             model_name=  "Nanonets-OCR-s"
 
         # file_type can be pdf, excel, etc.
-        if output_dir is None and myfile is None and file_bytes is not None and suffix is not None:
+        if file_bytes and suffix:
             with tempfile.TemporaryDirectory() as dp:
-                with tempfile.NamedTemporaryFile(suffix= suffix, mode= 'wb') as fp:
-                    fp.write(file_bytes)
-                    myfile= Path(fp.name)
-                    output_dir= Path(dp)
-                    if file_type == 'pdf':
-                        extractor= MarkdownPDFExtractor(str(myfile), output_path= str(output_dir), page_delimiter= "-- NEXT PAGE --", model_name= model_name)
-                        extractor.extract()
-                        with open(output_dir / (myfile.stem + '.md')) as output_file:
-                            self.output= output_file.read()
-                    elif file_type == 'excel':
-                        self.input_filepath= myfile
-                        self.output= self.convert_excel_to_markdown()
+                output_dir = Path(dp)
+                myfile = output_dir / f"input{suffix}"
+                myfile.write_bytes(file_bytes)
+
+                if file_type == 'pdf':
+                    extractor = MarkdownPDFExtractor(str(myfile), output_path=str(output_dir), page_delimiter="-- NEXT PAGE --", model_name=model_name)
+                    extractor.extract()
+                    with open(output_dir / (myfile.stem + '.md')) as output_file:
+                        self.output = output_file.read()
+                elif file_type == 'excel':
+                    self.input_filepath = myfile
+                    self.output = self.convert_excel_to_markdown()
+
 
         elif output_dir is not None and myfile is not None:
             print("got output path for conversion: ", output_dir)
@@ -73,6 +74,9 @@ class Convertor():
 
             elif mt in EXCEL_FILE_TYPES:
                 self.output = self.convert_excel_to_markdown()
+                if myfile and output_dir:
+                    with open(output_dir / (myfile.stem + '.md'), "w") as output_file:
+                        output_file.write(self.output)
 
             else:
                 print(mt)

{pembot-0.1.3 → pembot-0.1.5}/pembot/__init__.py

@@ -1,6 +1,6 @@
 """
 A Python Package to convert PEM blog content to usseful information by leveraging LLMs
 """
-__version__ = '0.1.3'
+__version__ = '0.1.5'
 from .main import save_to_json_file, make_query
 __all__ = ["save_to_json_file", "make_query"]

{pembot-0.1.3 → pembot-0.1.5}/pembot/config/config.yaml

@@ -2,4 +2,4 @@ OUTPUT_DIR: /home/cyto/dev/pembotdir
 PAGE_DELIMITER: ___________________________ NEXT PAGE ___________________________
 app:
   name: pembot
-  version: 0.1.3
+  version: 0.1.5

{pembot-0.1.3 → pembot-0.1.5}/pembot/requirements.txt

@@ -46,7 +46,7 @@ pandas==2.3.0
 pathlib==1.0.1
 pdfminer.six==20250506
 pdfplumber==0.11.7
-pembot==0.1.3
+pembot==0.1.5
 pillow==11.3.0
 primp==0.15.0
 pyasn1==0.6.1

pembot-0.1.3/pembot/.git/COMMIT_EDITMSG

@@ -1 +0,0 @@
-cyto/fixed the excel to markdown conversion

pembot-0.1.3/pembot/.git/refs/heads/main

@@ -1 +0,0 @@
-c3cc0da3d955ecec0f865c46c030a0c073697495

pembot-0.1.3/pembot/.git/refs/remotes/origin/main

@@ -1 +0,0 @@
-c3cc0da3d955ecec0f865c46c030a0c073697495