yomitoku 0.9.0__py3-none-any.whl → 0.9.1__py3-none-any.whl

yomitoku/cli/main.py

@@ -92,7 +92,7 @@ def process_single_file(args, analyzer, path, format):
 
         if ocr is not None:
             out_path = os.path.join(
-                args.outdir, f"{dirname}_{filename}_p{page+1}_ocr.jpg"
+                args.outdir, f"{dirname}_{filename}_p{page + 1}_ocr.jpg"
             )
 
             save_image(ocr, out_path)
@@ -100,13 +100,15 @@ def process_single_file(args, analyzer, path, format):
 
         if layout is not None:
             out_path = os.path.join(
-                args.outdir, f"{dirname}_{filename}_p{page+1}_layout.jpg"
+                args.outdir, f"{dirname}_{filename}_p{page + 1}_layout.jpg"
             )
 
             save_image(layout, out_path)
             logger.info(f"Output file: {out_path}")
 
-        out_path = os.path.join(args.outdir, f"{dirname}_{filename}_p{page+1}.{format}")
+        out_path = os.path.join(
+            args.outdir, f"{dirname}_{filename}_p{page + 1}.{format}"
+        )
 
         if format == "json":
             if args.combine:
@@ -341,6 +343,12 @@ def main():
         action="store_true",
         help="if set, ignore meta information(header, footer) in the output",
     )
+    parser.add_argument(
+        "--reading_order",
+        default="auto",
+        type=str,
+        choices=["auto", "left2right", "top2bottom", "right2left"],
+    )
 
     args = parser.parse_args()
 
@@ -394,6 +402,7 @@ def main():
         visualize=args.vis,
         device=args.device,
         ignore_meta=args.ignore_meta,
+        reading_order=args.reading_order,
     )
 
     os.makedirs(args.outdir, exist_ok=True)
@@ -408,7 +417,7 @@ def main():
                 logger.info(f"Processing file: {file_path}")
                 process_single_file(args, analyzer, file_path, format)
                 end = time.time()
-                logger.info(f"Total Processing time: {end-start:.2f} sec")
+                logger.info(f"Total Processing time: {end - start:.2f} sec")
             except Exception:
                 continue
     else:
@@ -416,7 +425,7 @@ def main():
         logger.info(f"Processing file: {path}")
         process_single_file(args, analyzer, path, format)
         end = time.time()
-        logger.info(f"Total Processing time: {end-start:.2f} sec")
+        logger.info(f"Total Processing time: {end - start:.2f} sec")
 
 
 if __name__ == "__main__":

yomitoku/data/dataset.py

@@ -8,9 +8,11 @@ from .functions import (
     validate_quads,
 )
 
+from concurrent.futures import ThreadPoolExecutor
+
 
 class ParseqDataset(Dataset):
-    def __init__(self, cfg, img, quads):
+    def __init__(self, cfg, img, quads, num_workers=8):
         self.img = img[:, :, ::-1]
         self.quads = quads
         self.cfg = cfg
@@ -22,19 +24,27 @@ class ParseqDataset(Dataset):
             ]
         )
 
-        validate_quads(self.img, self.quads)
+        with ThreadPoolExecutor(max_workers=num_workers) as executor:
+            data = list(executor.map(self.preprocess, self.quads))
 
-    def __len__(self):
-        return len(self.quads)
+        self.data = [tensor for tensor in data if tensor is not None]
+
+    def preprocess(self, quad):
+        if validate_quads(self.img, quad) is None:
+            return None
+
+        roi_img = extract_roi_with_perspective(self.img, quad)
 
-    def __getitem__(self, index):
-        polygon = self.quads[index]
-        roi_img = extract_roi_with_perspective(self.img, polygon)
         if roi_img is None:
-            return
+            return None
 
         roi_img = rotate_text_image(roi_img, thresh_aspect=2)
         resized = resize_with_padding(roi_img, self.cfg.data.img_size)
-        tensor = self.transform(resized)
 
-        return tensor
+        return resized
+
+    def __len__(self):
+        return len(self.data)
+
+    def __getitem__(self, index):
+        return self.transform(self.data[index])

yomitoku/data/functions.py

@@ -191,7 +191,7 @@ def array_to_tensor(img: np.ndarray) -> torch.Tensor:
     return tensor
 
 
-def validate_quads(img: np.ndarray, quads: list[list[list[int]]]):
+def validate_quads(img: np.ndarray, quad: list[list[list[int]]]):
     """
     Validate the vertices of the quadrilateral.
 
@@ -204,23 +204,23 @@ def validate_quads(img: np.ndarray, quads: list[list[list[int]]]):
     """
 
     h, w = img.shape[:2]
-    for quad in quads:
-        if len(quad) != 4:
-            raise ValueError("The number of vertices must be 4.")
-
-        for point in quad:
-            if len(point) != 2:
-                raise ValueError("The number of coordinates must be 2.")
-
-        quad = np.array(quad, dtype=int)
-        x1 = np.min(quad[:, 0])
-        x2 = np.max(quad[:, 0])
-        y1 = np.min(quad[:, 1])
-        y2 = np.max(quad[:, 1])
-        h, w = img.shape[:2]
+    if len(quad) != 4:
+        # raise ValueError("The number of vertices must be 4.")
+        return None
+
+    for point in quad:
+        if len(point) != 2:
+            return None
+
+    quad = np.array(quad, dtype=int)
+    x1 = np.min(quad[:, 0])
+    x2 = np.max(quad[:, 0])
+    y1 = np.min(quad[:, 1])
+    y2 = np.max(quad[:, 1])
+    h, w = img.shape[:2]
 
-        if x1 < 0 or x2 > w or y1 < 0 or y2 > h:
-            raise ValueError(f"The vertices are out of the image. {quad.tolist()}")
+    if x1 < 0 or x2 > w or y1 < 0 or y2 > h:
+        return None
 
     return True
 
@@ -237,19 +237,18 @@ def extract_roi_with_perspective(img, quad):
         np.ndarray: extracted image
     """
     dst = img.copy()
-    quad = np.array(quad, dtype=np.float32)
+    quad = np.array(quad, dtype=np.int64)
+
     width = np.linalg.norm(quad[0] - quad[1])
     height = np.linalg.norm(quad[1] - quad[2])
 
     width = int(width)
     height = int(height)
-
     pts1 = np.float32(quad)
     pts2 = np.float32([[0, 0], [width, 0], [width, height], [0, height]])
 
     M = cv2.getPerspectiveTransform(pts1, pts2)
     dst = cv2.warpPerspective(dst, M, (width, height))
-
     return dst
 
 

yomitoku/document_analyzer.py

@@ -86,8 +86,12 @@ def extract_paragraph_within_figure(paragraphs, figures):
                 check_list[i] = True
 
         figure["direction"] = judge_page_direction(contained_paragraphs)
+        reading_order = (
+            "left2right" if figure["direction"] == "horizontal" else "right2left"
+        )
+
         figure_paragraphs = prediction_reading_order(
-            contained_paragraphs, figure["direction"]
+            contained_paragraphs, reading_order
         )
         figure["paragraphs"] = sorted(figure_paragraphs, key=lambda x: x.order)
         figure = FigureSchema(**figure)
@@ -126,8 +130,8 @@ def extract_words_within_element(pred_words, element):
     cnt_vertical = word_direction.count("vertical")
 
     element_direction = "horizontal" if cnt_horizontal > cnt_vertical else "vertical"
-
-    prediction_reading_order(contained_words, element_direction)
+    order = "left2right" if element_direction == "horizontal" else "right2left"
+    prediction_reading_order(contained_words, order)
     contained_words = sorted(contained_words, key=lambda x: x.order)
 
     contained_words = "\n".join([content.contents for content in contained_words])
@@ -328,6 +332,7 @@ class DocumentAnalyzer:
         device="cuda",
         visualize=False,
         ignore_meta=False,
+        reading_order="auto",
     ):
         default_configs = {
             "ocr": {
@@ -352,6 +357,8 @@ class DocumentAnalyzer:
             },
         }
 
+        self.reading_order = reading_order
+
         if isinstance(configs, dict):
             recursive_update(default_configs, configs)
         else:
@@ -452,9 +459,17 @@ class DocumentAnalyzer:
 
         elements = page_contents + layout_res.tables + figures
 
-        prediction_reading_order(headers, page_direction)
-        prediction_reading_order(footers, page_direction)
-        prediction_reading_order(elements, page_direction, self.img)
+        prediction_reading_order(headers, "left2right")
+        prediction_reading_order(footers, "left2right")
+
+        if self.reading_order == "auto":
+            reading_order = (
+                "right2left" if page_direction == "vertical" else "top2bottom"
+            )
+        else:
+            reading_order = self.reading_order
+
+        prediction_reading_order(elements, reading_order, self.img)
 
         for i, element in enumerate(elements):
             element.order += len(headers)

yomitoku/reading_order.py

@@ -17,7 +17,6 @@ def _priority_dfs(nodes, direction):
 
     pending_nodes = sorted(nodes, key=lambda x: x.prop["distance"])
     visited = [False] * len(nodes)
-
     start = pending_nodes.pop(0)
     stack = [start]
 
@@ -53,11 +52,11 @@ def _priority_dfs(nodes, direction):
                         children.append(node)
                         stack.remove(node)
 
-                if direction == "horizontal":
+                if direction in "top2bottom":
                     children = sorted(
                         children, key=lambda x: x.prop["box"][0], reverse=True
                     )
-                else:
+                elif direction in ["right2left", "left2right"]:
                     children = sorted(
                         children, key=lambda x: x.prop["box"][1], reverse=True
                     )
@@ -121,7 +120,7 @@ def _exist_other_node_between_horizontal(node, other_node, nodes):
     return False
 
 
-def _create_graph_horizontal(nodes):
+def _create_graph_top2bottom(nodes):
     for i, node in enumerate(nodes):
         for j, other_node in enumerate(nodes):
             if i == j:
@@ -146,7 +145,7 @@ def _create_graph_horizontal(nodes):
         node.children = sorted(node.children, key=lambda x: x.prop["box"][0])
 
 
-def _create_graph_vertical(nodes):
+def _create_graph_right2left(nodes):
     max_x = max([node.prop["box"][2] for node in nodes])
 
     for i, node in enumerate(nodes):
@@ -172,15 +171,46 @@ def _create_graph_vertical(nodes):
         node.children = sorted(node.children, key=lambda x: x.prop["box"][1])
 
 
+def _create_graph_left2right(nodes, x_weight=1, y_weight=5):
+    for i, node in enumerate(nodes):
+        for j, other_node in enumerate(nodes):
+            if i == j:
+                continue
+
+            if is_intersected_horizontal(node.prop["box"], other_node.prop["box"]):
+                tx = node.prop["box"][2]
+                ox = other_node.prop["box"][2]
+
+                if _exist_other_node_between_horizontal(node, other_node, nodes):
+                    continue
+
+                if ox < tx:
+                    other_node.add_link(node)
+                else:
+                    node.add_link(other_node)
+
+            node_distance = (
+                node.prop["box"][0] * x_weight + node.prop["box"][1] * y_weight
+            )
+            node.prop["distance"] = node_distance
+
+    for node in nodes:
+        node.children = sorted(node.children, key=lambda x: x.prop["box"][1])
+
+
 def prediction_reading_order(elements, direction, img=None):
     if len(elements) < 2:
         return elements
 
     nodes = [Node(i, element.dict()) for i, element in enumerate(elements)]
-    if direction == "horizontal":
-        _create_graph_horizontal(nodes)
+    if direction == "top2bottom":
+        _create_graph_top2bottom(nodes)
+    elif direction == "right2left":
+        _create_graph_right2left(nodes)
+    elif direction == "left2right":
+        _create_graph_left2right(nodes)
     else:
-        _create_graph_vertical(nodes)
+        raise ValueError(f"Invalid direction: {direction}")
 
     # For debugging
     # if img is not None:

yomitoku/utils/misc.py

@@ -80,7 +80,7 @@ def calc_intersection(rect_a, rect_b):
     return [ix1, iy1, ix2, iy2]
 
 
-def is_intersected_horizontal(rect_a, rect_b):
+def is_intersected_horizontal(rect_a, rect_b, threshold=0.5):
     _, ay1, _, ay2 = map(int, rect_a)
     _, by1, _, by2 = map(int, rect_b)
 
@@ -88,9 +88,11 @@ def is_intersected_horizontal(rect_a, rect_b):
     iy1 = max(ay1, by1)
     iy2 = min(ay2, by2)
 
+    min_height = min(ay2 - ay1, by2 - by1)
+
     overlap_height = max(0, iy2 - iy1)
 
-    if overlap_height == 0:
+    if (overlap_height / min_height) < threshold:
         return False
 
     return True
@@ -119,3 +121,48 @@ def quad_to_xyxy(quad):
     y2 = max([y for _, y in quad])
 
     return x1, y1, x2, y2
+
+
+def convert_table_array(table):
+    n_rows = table.n_row
+    n_cols = table.n_col
+
+    table_array = [["" for _ in range(n_cols)] for _ in range(n_rows)]
+
+    for cell in table.cells:
+        row = cell.row - 1
+        col = cell.col - 1
+        row_span = cell.row_span
+        col_span = cell.col_span
+        contents = cell.contents
+
+        for i in range(row, row + row_span):
+            for j in range(col, col + col_span):
+                table_array[i][j] = contents
+
+    return table_array
+
+
+def convert_table_array_to_dict(table_array, header_row=1):
+    n_cols = len(table_array[0])
+    n_rows = len(table_array)
+
+    header_cols = []
+    for i in range(n_cols):
+        header = []
+        for j in range(header_row):
+            header.append(table_array[j][i])
+
+        if len(header) > 0:
+            header_cols.append("_".join(header))
+        else:
+            header_cols.append(f"col_{i}")
+
+    table_dict = []
+    for i in range(header_row, n_rows):
+        row_dict = {}
+        for j in range(n_cols):
+            row_dict[header_cols[j]] = table_array[i][j]
+        table_dict.append(row_dict)
+
+    return table_dict

{yomitoku-0.9.0.dist-info → yomitoku-0.9.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: yomitoku
-Version: 0.9.0
+Version: 0.9.1
 Summary: Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.
 Author-email: Kotaro Kinoshita <kotaro.kinoshita@mlism.com>
 License: CC BY-NC-SA 4.0
@@ -66,6 +66,7 @@ Markdown でエクスポートした結果は関してはリポジトリ内の[s
 
 ## 📣 リリース情報
 
+- 2025 年  4 月  4 日 YomiToku v0.8.0 手書き文字認識のサポート
 - 2024 年 11 月 26 日 YomiToku v0.5.1 (beta) を公開
 
 ## 💡 インストールの方法

{yomitoku-0.9.0.dist-info → yomitoku-0.9.1.dist-info}/RECORD

@@ -1,16 +1,16 @@
 yomitoku/__init__.py,sha256=kXOM8RbpwwLABG3p3vPT3dJWBk4JX2MFGrOeBEW0hKM,543
 yomitoku/base.py,sha256=9U3sfe69O6vuO430JzzKQQNkgPsLM9WdLfOUUhp3Ljs,3878
 yomitoku/constants.py,sha256=zlW5QRc_u_F3C2RAgBFWyHJZexBnJT5N15GC-9d3iLo,686
-yomitoku/document_analyzer.py,sha256=wQMmXACDsDmyaxg2OnG9Og5Nx53WPUkQdUmgYtljACQ,16412
+yomitoku/document_analyzer.py,sha256=xliAelQdfsK64FtVuFvstDBr9uf2TwhqW31g2g91_CY,16888
 yomitoku/layout_analyzer.py,sha256=VhNf1ZQFoozj6WUGk5ll1p2p1jk5X3j-JPcDbTAoSl4,1856
 yomitoku/layout_parser.py,sha256=0MgbCsD90srQdsxkGEL0TgKm4rkmGzsQYx0sjKQ03yc,7718
 yomitoku/ocr.py,sha256=JSTjkupcxHITQm6ERnzU7As0c3KWf8-oxc0AqNoWHXo,2272
-yomitoku/reading_order.py,sha256=OfhOS9ttPDoPSuHrIRKyOzG19GGeRufbuSKDqhsohh4,6404
+yomitoku/reading_order.py,sha256=_T09PqT7guk57zWo4HdSazLSQTwM91piyELA_wNHQAQ,7521
 yomitoku/table_structure_recognizer.py,sha256=tHjex6deT_FjRK5ePz9bUXA_QIhgv_vYtK-ynm4ALxg,9625
 yomitoku/text_detector.py,sha256=6IwEJJKp_F8YH0Oki0QV-Mqi--P2LGbNKo-_kxBB_eo,4383
 yomitoku/text_recognizer.py,sha256=eaxozNu-Ms6iv8efbKZzn8pJNW1Wo4f86bGhzSMtv3s,5992
 yomitoku/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-yomitoku/cli/main.py,sha256=9X8QWwsTAv82uNn5Ns9T_laGJPKHDyeEwenaQxnAmn4,12062
+yomitoku/cli/main.py,sha256=VZG8DZf-k_QytlDZtB91eBNY69MRpbryQg1rkn3fs20,12304
 yomitoku/cli/mcp.py,sha256=5h704SsUGNAqVnoO_5S-HY2-bApy_Rf8ajDxl1pkT2k,4888
 yomitoku/configs/__init__.py,sha256=x5-ccjGiP6xxRtDPT7f1Enl7SsE0hSk0G8f7eF9V85I,886
 yomitoku/configs/cfg_layout_parser_rtdtrv2.py,sha256=8PRxB2Ar9UF7-DLtbgSokhrzdXb0veWI6Wc-X8qigRw,2329
@@ -22,8 +22,8 @@ yomitoku/configs/cfg_text_recognizer_parseq.py,sha256=hpFs3nKqh4XdU3BZMTultegtLE
 yomitoku/configs/cfg_text_recognizer_parseq_small.py,sha256=uCm_VC_G79IbZpOiK8fgYzAJ4b98H5pf328wyQomtfo,1259
 yomitoku/configs/cfg_text_recognizer_parseq_v2.py,sha256=GfHzbByOKjH21PRTxT8x_fU4r4Mda6F750Z8pjNeb8g,1249
 yomitoku/data/__init__.py,sha256=KAofFc9rk9ZdTKBjemu9RM8Vj9XnKbWC2MPZ2RWtOdE,82
-yomitoku/data/dataset.py,sha256=-I4f-FDtgsPnJ2MnXB7FtwihMW3koDaSI1OEoqKneIg,1014
-yomitoku/data/functions.py,sha256=HIrffs0zCJOq8IvQiI_z-b4MwTb-H2wmZjEE_5VpxFs,8040
+yomitoku/data/dataset.py,sha256=lpBcpkMuQzRIyLJ4_mqtuhR9s2ZmzgBgc-XYuE_b2Sc,1326
+yomitoku/data/functions.py,sha256=RExCUxI3-gccIMw-H0ribX2jeGKkrJWhS4fNn_12c3Y,7878
 yomitoku/export/__init__.py,sha256=gmlikMHRXfzfJ_8q4fyDlnpGms-x1oggQOwJEWHMgBU,508
 yomitoku/export/export_csv.py,sha256=VY8mntUCPDbDco_dyvq5O0_Q4wga9_GTyjHCS-y4UiQ,3399
 yomitoku/export/export_html.py,sha256=LQDyZgbzmI0qJ0-FEK-54r9816H3L9hD10ChMcw0KyA,5620
@@ -50,9 +50,9 @@ yomitoku/resource/charset.txt,sha256=sU91kSi-9Wk4733bCXy4j_UDmvcsj96sHOq1ppUJlOY
 yomitoku/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 yomitoku/utils/graph.py,sha256=LKNB8ZhSQwOZMfeAimPMF5UCVVr2ZaUWoGDkz8z-uGU,456
 yomitoku/utils/logger.py,sha256=uOmtQDr0A0JD7wyFshedL08BiNrQorHnpktRXba8bjU,424
-yomitoku/utils/misc.py,sha256=cIUrvSJwfWwTui7ueYistf9XPapPR3XgqD2wQjWit40,2901
+yomitoku/utils/misc.py,sha256=r92x45kQR8lC5jO1MZaHBDtcCWBkQXg_WS9H4RXJzSY,4127
 yomitoku/utils/visualizer.py,sha256=DjDwHiAu1iFRKh96H3Egq4vuI2s_-9dLCDeykhKi8jo,5251
-yomitoku-0.9.0.dist-info/METADATA,sha256=vUbrNm2w-7OIqEEXNzFQBDm8y57mTuh1UeJYHBGRo9U,8622
-yomitoku-0.9.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-yomitoku-0.9.0.dist-info/entry_points.txt,sha256=N3PzzSo-fdgri5liPpZ3ItMmRH6oVX14pIU_5pUJiAs,99
-yomitoku-0.9.0.dist-info/RECORD,,
+yomitoku-0.9.1.dist-info/METADATA,sha256=ozEkYekTPuEP1GwnCCQKgJC9DzEQpyActU_DltQGMHc,8700
+yomitoku-0.9.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+yomitoku-0.9.1.dist-info/entry_points.txt,sha256=N3PzzSo-fdgri5liPpZ3ItMmRH6oVX14pIU_5pUJiAs,99
+yomitoku-0.9.1.dist-info/RECORD,,