feat: enhance PDF parsing functionality with new backend options and improved output handling

demo/batch_demo.py

-import os
-from pathlib import Path
-from magic_pdf.data.batch_build_dataset import batch_build_dataset
-from magic_pdf.tools.common import batch_do_parse
-
-
-def batch(pdf_dir, output_dir, method, lang):
-    os.makedirs(output_dir, exist_ok=True)
-    doc_paths = []
-    for doc_path in Path(pdf_dir).glob('*'):
-        if doc_path.suffix == '.pdf':
-            doc_paths.append(doc_path)
-
-    # build dataset with 2 workers
-    datasets = batch_build_dataset(doc_paths, 4, lang)
-
-    # os.environ["MINERU_MIN_BATCH_INFERENCE_SIZE"] = "200"  # every 200 pages will be parsed in one batch
-    batch_do_parse(output_dir, [str(doc_path.stem) for doc_path in doc_paths], datasets, method)
-
-
-if __name__ == '__main__':
-    batch("pdfs", "output", "auto", "")
-

demo/demo.py

 # Copyright (c) Opendatalab. All rights reserved.
+import copy
+import json
 import os
-
-from magic_pdf.data.data_reader_writer import FileBasedDataWriter, FileBasedDataReader
-from magic_pdf.data.dataset import PymuDocDataset
-from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze
-from magic_pdf.config.enums import SupportedPdfParseMethod
-
-# args
-__dir__ = os.path.dirname(os.path.abspath(__file__))
-pdf_file_name = os.path.join(__dir__, "pdfs", "demo1.pdf")  # replace with the real pdf path
-name_without_extension = os.path.basename(pdf_file_name).split('.')[0]
-
-# prepare env
-local_image_dir = os.path.join(__dir__, "output", name_without_extension, "images")
-local_md_dir = os.path.join(__dir__, "output", name_without_extension)
-image_dir = str(os.path.basename(local_image_dir))
-os.makedirs(local_image_dir, exist_ok=True)
-
-image_writer, md_writer = FileBasedDataWriter(local_image_dir), FileBasedDataWriter(local_md_dir)
-
-# read bytes
-reader1 = FileBasedDataReader("")
-pdf_bytes = reader1.read(pdf_file_name)  # read the pdf content
-
-# proc
-## Create Dataset Instance
-ds = PymuDocDataset(pdf_bytes)
-
-## inference
-if ds.classify() == SupportedPdfParseMethod.OCR:
-    infer_result = ds.apply(doc_analyze, ocr=True)
-
-    ## pipeline
-    pipe_result = infer_result.pipe_ocr_mode(image_writer)
-
-else:
-    infer_result = ds.apply(doc_analyze, ocr=False)
-
-    ## pipeline
-    pipe_result = infer_result.pipe_txt_mode(image_writer)
-
-### get model inference result
-model_inference_result = infer_result.get_infer_res()
-
-### draw layout result on each page
-pipe_result.draw_layout(os.path.join(local_md_dir, f"{name_without_extension}_layout.pdf"))
-
-### draw spans result on each page
-pipe_result.draw_span(os.path.join(local_md_dir, f"{name_without_extension}_spans.pdf"))
-
-### get markdown content
-md_content = pipe_result.get_markdown(image_dir)
-
-### dump markdown
-pipe_result.dump_md(md_writer, f"{name_without_extension}.md", image_dir)
-
-### get content list content
-content_list_content = pipe_result.get_content_list(image_dir)
-
-### dump content list
-pipe_result.dump_content_list(md_writer, f"{name_without_extension}_content_list.json", image_dir)
-
-### get middle json
-middle_json_content = pipe_result.get_middle_json()
-
-### dump middle json
-pipe_result.dump_middle_json(md_writer, f'{name_without_extension}_middle.json')
+from pathlib import Path
+
+from loguru import logger
+
+from mineru.cli.common import convert_pdf_bytes_to_bytes_by_pypdfium2, prepare_env, read_fn
+from mineru.data.data_reader_writer import FileBasedDataWriter
+from mineru.utils.draw_bbox import draw_layout_bbox, draw_span_bbox
+from mineru.utils.enum_class import MakeMode
+from mineru.backend.vlm.vlm_analyze import doc_analyze as vlm_doc_analyze
+from mineru.backend.pipeline.pipeline_analyze import doc_analyze as pipeline_doc_analyze
+from mineru.backend.pipeline.pipeline_middle_json_mkcontent import union_make as pipeline_union_make
+from mineru.backend.pipeline.model_json_to_middle_json import result_to_middle_json as pipeline_result_to_middle_json
+from mineru.backend.vlm.vlm_middle_json_mkcontent import union_make as vlm_union_make
+from mineru.utils.models_download_utils import auto_download_and_get_model_root_path
+
+
+def do_parse(
+    output_dir,  # Output directory for storing parsing results
+    pdf_file_names: list[str],  # List of PDF file names to be parsed
+    pdf_bytes_list: list[bytes],  # List of PDF bytes to be parsed
+    p_lang_list: list[str],  # List of languages for each PDF, default is 'ch' (Chinese)
+    backend="pipeline",  # The backend for parsing PDF, default is 'pipeline'
+    parse_method="auto",  # The method for parsing PDF, default is 'auto'
+    p_formula_enable=True,  # Enable formula parsing
+    p_table_enable=True,  # Enable table parsing
+    server_url=None,  # Server URL for vlm-sglang-client backend
+    f_draw_layout_bbox=True,  # Whether to draw layout bounding boxes
+    f_draw_span_bbox=True,  # Whether to draw span bounding boxes
+    f_dump_md=True,  # Whether to dump markdown files
+    f_dump_middle_json=True,  # Whether to dump middle JSON files
+    f_dump_model_output=True,  # Whether to dump model output files
+    f_dump_orig_pdf=True,  # Whether to dump original PDF files
+    f_dump_content_list=True,  # Whether to dump content list files
+    f_make_md_mode=MakeMode.MM_MD,  # The mode for making markdown content, default is MM_MD
+    start_page_id=0,  # Start page ID for parsing, default is 0
+    end_page_id=None,  # End page ID for parsing, default is None (parse all pages until the end of the document)
+):
+
+    if backend == "pipeline":
+        for idx, pdf_bytes in enumerate(pdf_bytes_list):
+            new_pdf_bytes = convert_pdf_bytes_to_bytes_by_pypdfium2(pdf_bytes, start_page_id, end_page_id)
+            pdf_bytes_list[idx] = new_pdf_bytes
+
+        infer_results, all_image_lists, all_pdf_docs, lang_list, ocr_enabled_list = pipeline_doc_analyze(pdf_bytes_list, p_lang_list, parse_method=parse_method, formula_enable=p_formula_enable,table_enable=p_table_enable)
+
+        for idx, model_list in enumerate(infer_results):
+            model_json = copy.deepcopy(model_list)
+            pdf_file_name = pdf_file_names[idx]
+            local_image_dir, local_md_dir = prepare_env(output_dir, pdf_file_name, parse_method)
+            image_writer, md_writer = FileBasedDataWriter(local_image_dir), FileBasedDataWriter(local_md_dir)
+
+            images_list = all_image_lists[idx]
+            pdf_doc = all_pdf_docs[idx]
+            _lang = lang_list[idx]
+            _ocr_enable = ocr_enabled_list[idx]
+            middle_json = pipeline_result_to_middle_json(model_list, images_list, pdf_doc, image_writer, _lang, _ocr_enable, p_formula_enable)
+
+            pdf_info = middle_json["pdf_info"]
+
+            pdf_bytes = pdf_bytes_list[idx]
+            if f_draw_layout_bbox:
+                draw_layout_bbox(pdf_info, pdf_bytes, local_md_dir, f"{pdf_file_name}_layout.pdf")
+
+            if f_draw_span_bbox:
+                draw_span_bbox(pdf_info, pdf_bytes, local_md_dir, f"{pdf_file_name}_span.pdf")
+
+            if f_dump_orig_pdf:
+                md_writer.write(
+                    f"{pdf_file_name}_origin.pdf",
+                    pdf_bytes,
+                )
+
+            if f_dump_md:
+                image_dir = str(os.path.basename(local_image_dir))
+                md_content_str = pipeline_union_make(pdf_info, f_make_md_mode, image_dir)
+                md_writer.write_string(
+                    f"{pdf_file_name}.md",
+                    md_content_str,
+                )
+
+            if f_dump_content_list:
+                image_dir = str(os.path.basename(local_image_dir))
+                content_list = pipeline_union_make(pdf_info, MakeMode.CONTENT_LIST, image_dir)
+                md_writer.write_string(
+                    f"{pdf_file_name}_content_list.json",
+                    json.dumps(content_list, ensure_ascii=False, indent=4),
+                )
+
+            if f_dump_middle_json:
+                md_writer.write_string(
+                    f"{pdf_file_name}_middle.json",
+                    json.dumps(middle_json, ensure_ascii=False, indent=4),
+                )
+
+            if f_dump_model_output:
+                md_writer.write_string(
+                    f"{pdf_file_name}_model.json",
+                    json.dumps(model_json, ensure_ascii=False, indent=4),
+                )
+
+            logger.info(f"local output dir is {local_md_dir}")
+    else:
+        if backend.startswith("vlm-"):
+            backend = backend[4:]
+
+        f_draw_span_bbox = False
+        parse_method = "vlm"
+        for idx, pdf_bytes in enumerate(pdf_bytes_list):
+            pdf_file_name = pdf_file_names[idx]
+            pdf_bytes = convert_pdf_bytes_to_bytes_by_pypdfium2(pdf_bytes, start_page_id, end_page_id)
+            local_image_dir, local_md_dir = prepare_env(output_dir, pdf_file_name, parse_method)
+            image_writer, md_writer = FileBasedDataWriter(local_image_dir), FileBasedDataWriter(local_md_dir)
+            model_path = auto_download_and_get_model_root_path('/', 'vlm')
+            middle_json, infer_result = vlm_doc_analyze(pdf_bytes, image_writer=image_writer, backend=backend, model_path=model_path, server_url=server_url)
+
+            pdf_info = middle_json["pdf_info"]
+
+            if f_draw_layout_bbox:
+                draw_layout_bbox(pdf_info, pdf_bytes, local_md_dir, f"{pdf_file_name}_layout.pdf")
+
+            if f_draw_span_bbox:
+                draw_span_bbox(pdf_info, pdf_bytes, local_md_dir, f"{pdf_file_name}_span.pdf")
+
+            if f_dump_orig_pdf:
+                md_writer.write(
+                    f"{pdf_file_name}_origin.pdf",
+                    pdf_bytes,
+                )
+
+            if f_dump_md:
+                image_dir = str(os.path.basename(local_image_dir))
+                md_content_str = vlm_union_make(pdf_info, f_make_md_mode, image_dir)
+                md_writer.write_string(
+                    f"{pdf_file_name}.md",
+                    md_content_str,
+                )
+
+            if f_dump_content_list:
+                image_dir = str(os.path.basename(local_image_dir))
+                content_list = vlm_union_make(pdf_info, MakeMode.CONTENT_LIST, image_dir)
+                md_writer.write_string(
+                    f"{pdf_file_name}_content_list.json",
+                    json.dumps(content_list, ensure_ascii=False, indent=4),
+                )
+
+            if f_dump_middle_json:
+                md_writer.write_string(
+                    f"{pdf_file_name}_middle.json",
+                    json.dumps(middle_json, ensure_ascii=False, indent=4),
+                )
+
+            if f_dump_model_output:
+                model_output = ("\n" + "-" * 50 + "\n").join(infer_result)
+                md_writer.write_string(
+                    f"{pdf_file_name}_model_output.txt",
+                    model_output,
+                )
+
+            logger.info(f"local output dir is {local_md_dir}")
+
+
+def parse_doc(
+        path_list: list[Path],
+        output_dir,
+        lang="ch",
+        backend="pipeline",
+        method="auto",
+        server_url=None,
+        start_page_id=0,  # Start page ID for parsing, default is 0
+        end_page_id=None  # End page ID for parsing, default is None (parse all pages until the end of the document)
+):
+    """
+        Parameter description:
+        path_list: List of document paths to be parsed, can be PDF or image files.
+        output_dir: Output directory for storing parsing results.
+        lang: Language option, default is 'ch', optional values include['ch', 'ch_server', 'ch_lite', 'en', 'korean', 'japan', 'chinese_cht', 'ta', 'te', 'ka']。
+            Input the languages in the pdf (if known) to improve OCR accuracy.  Optional.
+            Adapted only for the case where the backend is set to "pipeline"
+        backend: the backend for parsing pdf:
+            pipeline: More general.
+            vlm-transformers: More general.
+            vlm-sglang-engine: Faster(engine).
+            vlm-sglang-client: Faster(client).
+            without method specified, pipeline will be used by default.
+        method: the method for parsing pdf:
+            auto: Automatically determine the method based on the file type.
+            txt: Use text extraction method.
+            ocr: Use OCR method for image-based PDFs.
+            Without method specified, 'auto' will be used by default.
+            Adapted only for the case where the backend is set to "pipeline".
+        server_url: When the backend is `sglang-client`, you need to specify the server_url, for example:`http://127.0.0.1:30000`
+    """
+    try:
+        file_name_list = []
+        pdf_bytes_list = []
+        lang_list = []
+        for path in path_list:
+            file_name = str(Path(path).stem)
+            pdf_bytes = read_fn(path)
+            file_name_list.append(file_name)
+            pdf_bytes_list.append(pdf_bytes)
+            lang_list.append(lang)
+        do_parse(
+            output_dir=output_dir,
+            pdf_file_names=file_name_list,
+            pdf_bytes_list=pdf_bytes_list,
+            p_lang_list=lang_list,
+            backend=backend,
+            parse_method=method,
+            server_url=server_url,
+            start_page_id=start_page_id,
+            end_page_id=end_page_id
+        )
+    except Exception as e:
+        logger.exception(e)
+
+
+if __name__ == '__main__':
+    # args
+    __dir__ = os.path.dirname(os.path.abspath(__file__))
+    pdf_files_dir = os.path.join(__dir__, "pdfs")
+    output_dir = os.path.join(__dir__, "output")
+    pdf_suffixes = [".pdf"]
+    image_suffixes = [".png", ".jpeg", ".jpg"]
+
+    doc_path_list = []
+    for doc_path in Path(pdf_files_dir).glob('*'):
+        if doc_path.suffix in pdf_suffixes + image_suffixes:
+            doc_path_list.append(doc_path)
+    parse_doc(doc_path_list, output_dir)

mineru/cli/client.py

@@ -41,7 +41,8 @@ from .common import do_parse, read_fn, pdf_suffixes, image_suffixes
     auto: Automatically determine the method based on the file type.
     txt: Use text extraction method.
     ocr: Use OCR method for image-based PDFs.
-    Without method specified, 'auto' will be used by default.""",
+    Without method specified, 'auto' will be used by default.
+    Adapted only for the case where the backend is set to "pipeline".""",
     default='auto',
 )
 @click.option(