调整tbpu模块，移除imgInfo参数

UmiOCR-data/py_src/ocr/output/output_pdf_layered.py

@@ -74,6 +74,6 @@ def print(self, res): # 输出图片结果
  def onEnd(self): # 结束时保存。
  print("保存PDF：", self.outputPath)
  if self.pdf:
- self.pdf.subset_fonts() # 构建字体子集，减小文件大小。需要fontTools库
+ self.pdf.subset_fonts() # 构建字体子集，减小文件大小。需要 fontTools 库
  # ez_save默认启用压缩和垃圾回收 deflate=True, garbage=3
  self.pdf.ez_save(self.outputPath)

UmiOCR-data/py_src/ocr/tbpu/__init__.py

@@ -1,3 +1,5 @@
+# tbpu : text block processing unit 文本块后处理
+
 from .merge_line import MergeLine
 from .merge_para import MergePara
 from .merge_para_code import MergeParaCode

UmiOCR-data/py_src/ocr/tbpu/ignore_area.py

@@ -8,7 +8,7 @@ def __init__(self, areaList):
  self.tbpuName = "忽略区域"
  self.areaList = areaList
 
- def run(self, textBlocks, imgInfo):
+ def run(self, textBlocks):
  # 返回是否矩形框 a 包含 b
  def isInBox(a, b):
  return (

UmiOCR-data/py_src/ocr/tbpu/merge_line.py

@@ -86,7 +86,7 @@ def sortKey(A, B):
 
  resList.sort(key=cmp_to_key(sortKey))
 
- def run(self, textBlocks, imgInfo):
+ def run(self, textBlocks):
  # 单行合并
  resList = self.mergeLine(textBlocks)
  # 结果排序

UmiOCR-data/py_src/ocr/tbpu/merge_line_v_lr.py

@@ -9,7 +9,7 @@ def __init__(self):
  self.tbpuName = "单行-竖排-从左到右"
  self.rl = False # T为从右到左，F为从左到右
 
- def run(self, textBlocks, imgInfo):
+ def run(self, textBlocks):
  """传入 文块组、图片信息。返回文块组、debug信息字符串。"""
  # 所有文块，按左上角点的y坐标排序
  textBlocks.sort(key=lambda tb: tb["box"][0][1])

UmiOCR-data/py_src/ocr/tbpu/merge_para.py

@@ -100,7 +100,7 @@ def mergePara(self, textBlocks):
  resList.append(tb1) # 装填入结果
  return resList
 
- def run(self, textBlocks, imgInfo):
+ def run(self, textBlocks):
  # 段落合并
  resList = self.mergePara(textBlocks)
  # 返回新文块列表

UmiOCR-data/py_src/ocr/tbpu/merge_para_code.py

@@ -106,7 +106,7 @@ def mergePara(self, textBlocks): # 所有行合并
  res = [{"text": text, "box": box, "score": score}]
  return res
 
- def run(self, textBlocks, imgInfo):
+ def run(self, textBlocks):
  # 段落合并
  resList = self.mergePara(textBlocks)
  # 返回新文块列表

UmiOCR-data/py_src/ocr/tbpu/tbpu.py

@@ -10,7 +10,9 @@ class Tbpu:
  def __init__(self):
  self.tbpuName = "文块处理单元-未知"
 
- def run(self, textBlocks, img):
- """输入：textBlocks文块 , img图片信息\n
- 输出：textBlocks文块"""
+ def run(self, textBlocks):
+ """输入：textBlocks文块列表\n
+ 输出：排序后的textBlocks文块列表，每个块增加键：
+ 'end' 结尾间隔符
+ """
  return textBlocks

UmiOCR-data/qt_res/qml/TabPages/BatchDOC/BatchDOC.qml

@@ -50,7 +50,8 @@ TabPage {
  onTriggered: {
  addDocs(
  [
- "D:/Pictures/Screenshots/test",
+ // "D:/Pictures/Screenshots/test",
+ "../../PDF测试",
  ]
  )
  console.log("自动添加！！！！！！！！！！！！！")