chatterer 0.1.20__py3-none-any.whl → 0.1.21__py3-none-any.whl

chatterer/examples/pdf_to_markdown.py

@@ -16,8 +16,8 @@ class PdfToMarkdownArgs(BaseArguments):
     output: Optional[str] = None
     """Output path. For a file, path to the output markdown file. For a directory, output directory for .md files."""
     """Chatterer instance for communication."""
-    pages: Optional[str] = None
-    """Page indices to convert (e.g., '1,3,5-9')."""
+    page: Optional[str] = None
+    """Zero-based page indices to convert (e.g., '0,2,4-8')."""
     recursive: bool = False
     """If input is a directory, search for PDFs recursively."""
     chatterer: ArgumentSpec[Chatterer] = ArgumentSpec(
@@ -29,7 +29,6 @@ class PdfToMarkdownArgs(BaseArguments):
 
     def run(self) -> list[dict[str, str]]:
         input = Path(self.input).resolve()
-        page_indices = parse_page_indices(self.pages) if self.pages else None
         pdf_files: list[Path] = []
         is_dir = False
         if input.is_file():
@@ -61,8 +60,8 @@ class PdfToMarkdownArgs(BaseArguments):
         converter = PdfToMarkdown(chatterer=self.chatterer.unwrap())
         results: list[dict[str, str]] = []
         for pdf in pdf_files:
-            output = (out_base / (pdf.stem + ".md")) if is_dir else out_base
-            md = converter.convert(str(pdf), page_indices)
+            output: Path = (out_base / (pdf.stem + ".md")) if is_dir else out_base
+            md: str = converter.convert(pdf_input=str(pdf), page_indices=self.page)
             output.parent.mkdir(parents=True, exist_ok=True)
             output.write_text(md, encoding="utf-8")
             results.append({"input": pdf.as_posix(), "output": output.as_posix(), "result": md})
@@ -70,28 +69,6 @@ class PdfToMarkdownArgs(BaseArguments):
         return results
 
 
-def parse_page_indices(pages_str: str) -> list[int] | None:
-    if not pages_str:
-        return None
-    indices: set[int] = set()
-    for part in pages_str.split(","):
-        part = part.strip()
-        if not part:
-            continue
-        if "-" in part:
-            start_str, end_str = part.split("-", 1)
-            start = int(start_str.strip())
-            end = int(end_str.strip())
-            if start > end:
-                raise ValueError
-            indices.update(range(start, end + 1))
-        else:
-            indices.add(int(part))
-    if not indices:
-        raise ValueError
-    return sorted(indices)
-
-
 def main() -> None:
     PdfToMarkdownArgs().run()
 

chatterer/examples/pdf_to_text.py

@@ -15,8 +15,8 @@ class PdfToTextArgs(BaseArguments):
     """Path to the PDF file to convert to text."""
     output: Optional[Path]
     """Path to the output text file. If not provided, defaults to the input file with a .txt suffix."""
-    pages: Optional[str] = None
-    """Comma-separated list of page indices to extract from the PDF. Supports ranges, e.g., '1,3,5-9'."""
+    page: Optional[str] = None
+    """Comma-separated list of zero-based page indices to extract from the PDF. Supports ranges, e.g., '0,2,4-8'."""
 
     def run(self) -> None:
         input = self.input.resolve()
@@ -24,7 +24,7 @@ class PdfToTextArgs(BaseArguments):
         if not input.is_file():
             sys.exit(1)
         out.write_text(
-            pdf_to_text(path_or_file=input, page_indices=self.pages),
+            pdf_to_text(path_or_file=input, page_indices=self.page),
             encoding="utf-8",
         )
         logger.info(f"Extracted text from `{input}` to `{out}`")

{chatterer-0.1.20.dist-info → chatterer-0.1.21.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: chatterer
-Version: 0.1.20
+Version: 0.1.21
 Summary: The highest-level interface for various LLM APIs.
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown

{chatterer-0.1.20.dist-info → chatterer-0.1.21.dist-info}/RECORD

@@ -10,8 +10,8 @@ chatterer/examples/anything_to_markdown.py,sha256=4O9ze7AIHcwEzvVmm5JMMKo_rVSFwh
 chatterer/examples/get_code_snippets.py,sha256=pz05JjhKaWAknVKlk1ftEEzpSG4-sqD9oa_gyIQoCAs,1911
 chatterer/examples/login_with_playwright.py,sha256=EhvJLaH5TD7bmDi12uP8YLd0fRhdjR-oyIkBHLi1Jjs,5988
 chatterer/examples/make_ppt.py,sha256=vsT_iL_jS2ami5VYrReLMQcD576FfZUH7913F7_As0A,23278
-chatterer/examples/pdf_to_markdown.py,sha256=Y83GfpmMApSvwbgNCw8CgFLeunYvZP0RCrgkvcXatGU,3479
-chatterer/examples/pdf_to_text.py,sha256=JhM_meogmvDmQZ31NqAgYd5Wx_WWKnt20V79g-uVEdo,1581
+chatterer/examples/pdf_to_markdown.py,sha256=ZeGRO5CZxGQxJpScK0iB1lTzUkfSiXtuqoeKEQL1ICA,2787
+chatterer/examples/pdf_to_text.py,sha256=DznTyhu1REv8Wp4RimQWVgEU5j0_BmlwjfJYJvx3dbI,1590
 chatterer/examples/transcription_api.py,sha256=WUs12qHH4616eLMQDHOiyVGxaXstTpgeE47djYyli6c,3897
 chatterer/examples/upstage_parser.py,sha256=TrfeSIiF0xklhFCknop22TIOVibI4CJ_UKj5-lD8c8E,3487
 chatterer/examples/webpage_to_markdown.py,sha256=DnZfQ-trXBiOiszA2tMlgadgKH-ObTi6l4gGloT-cQw,2846
@@ -37,8 +37,8 @@ chatterer/utils/base64_image.py,sha256=m_qAT3ERBiq8D-H4H9Z7rLfL31_BiPmV_m4uQ5XRL
 chatterer/utils/bytesio.py,sha256=3MC2atOOFKo5YxuReo_y_t8Wem9p2Y1ahC5M2lGclwI,2618
 chatterer/utils/code_agent.py,sha256=7ka_WRI4TQmZ5H46mjY3hI6RO_pxw6pg3LAxjgW4AbM,10495
 chatterer/utils/imghdr.py,sha256=6JhJMXD4MZ0dQolT2VM87YrRYm3hPf3RTEWnP4lYRVc,3842
-chatterer-0.1.20.dist-info/METADATA,sha256=9EIDlz3bfnlo0YfskNaooTj0UgCTyq3UHwBjcul1ijs,11826
-chatterer-0.1.20.dist-info/WHEEL,sha256=zaaOINJESkSfm_4HQVc5ssNzHCPXhJm0kEUakpsEHaU,91
-chatterer-0.1.20.dist-info/entry_points.txt,sha256=KhxL2dctnZalnDSmPoB5dZBBa9hZpJETW3C5xkoRaW4,554
-chatterer-0.1.20.dist-info/top_level.txt,sha256=7nSQKP0bHxPRc7HyzdbKsJdkvPgYD0214o6slRizv9s,10
-chatterer-0.1.20.dist-info/RECORD,,
+chatterer-0.1.21.dist-info/METADATA,sha256=j3QGPYik-jm75MHIfAvbvUbv-EaxvlVKdEIc7_dMUjk,11826
+chatterer-0.1.21.dist-info/WHEEL,sha256=zaaOINJESkSfm_4HQVc5ssNzHCPXhJm0kEUakpsEHaU,91
+chatterer-0.1.21.dist-info/entry_points.txt,sha256=KhxL2dctnZalnDSmPoB5dZBBa9hZpJETW3C5xkoRaW4,554
+chatterer-0.1.21.dist-info/top_level.txt,sha256=7nSQKP0bHxPRc7HyzdbKsJdkvPgYD0214o6slRizv9s,10
+chatterer-0.1.21.dist-info/RECORD,,