Merge branch 'dev' into dev

magic_pdf/data/data_reader_writer/multi_bucket_s3.py

@@ -1,4 +1,4 @@
-import os
+
 from magic_pdf.config.exceptions import InvalidConfig, InvalidParams
 from magic_pdf.data.data_reader_writer.base import DataReader, DataWriter
 from magic_pdf.data.io.s3 import S3Reader, S3Writer
@@ -22,10 +22,10 @@ def __init__(self, default_prefix: str, s3_configs: list[S3Config]):
         """
         if len(default_prefix) == 0:
             raise InvalidConfig('default_prefix must be provided')
-    
-        arr = default_prefix.strip("/").split("/")
+
+        arr = default_prefix.strip('/').split('/')
         self.default_bucket = arr[0]
-        self.default_prefix = "/".join(arr[1:])
+        self.default_prefix = '/'.join(arr[1:])
 
         found_default_bucket_config = False
         for conf in s3_configs:
@@ -103,7 +103,8 @@ def read_at(self, path: str, offset: int = 0, limit: int = -1) -> bytes:
             s3_reader = self.__get_s3_client(bucket_name)
         else:
             s3_reader = self.__get_s3_client(self.default_bucket)
-            path = os.path.join(self.default_prefix, path)
+            if self.default_prefix:
+                path = self.default_prefix + '/' + path
         return s3_reader.read_at(path, offset, limit)
 
 
@@ -139,5 +140,6 @@ def write(self, path: str, data: bytes) -> None:
             s3_writer = self.__get_s3_client(bucket_name)
         else:
             s3_writer = self.__get_s3_client(self.default_bucket)
-            path = os.path.join(self.default_prefix, path)
+            if self.default_prefix:
+                path = self.default_prefix + '/' + path
         return s3_writer.write(path, data)

magic_pdf/pdf_parse_union_core_v2.py

@@ -91,7 +91,8 @@ def chars_to_content(span):
 
         content = ''
         for char in span['chars']:
-            # 如果下一个char的x0和上一个char的x1距离超过一个字符宽度，则需要在中间插入一个空格
+
+            # 如果下一个char的x0和上一个char的x1距离超过0.25个字符宽度，则需要在中间插入一个空格
             char1 = char
             char2 = span['chars'][span['chars'].index(char) + 1] if span['chars'].index(char) + 1 < len(span['chars']) else None
             if char2 and char2['bbox'][0] - char1['bbox'][2] > char_avg_width * 0.25 and char['c'] != ' ' and char2['c'] != ' ':

projects/web_api/app.py

@@ -13,7 +13,7 @@
 from magic_pdf.data.data_reader_writer import FileBasedDataWriter
 from magic_pdf.data.dataset import PymuDocDataset
 from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze
-from magic_pdf.model.operators import InferenceResult
+from magic_pdf.operators.models import InferenceResult
 
 model_config.__use_inside_model__ = True