Fix typo in code (#8327)

### What problem does this PR solve?

Fix typo in code

### Type of change

- [x] Refactoring

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>

api/db/init_data.py

@@ -84,14 +84,14 @@ def init_superuser():
         {"role": "user", "content": "Hello!"}], gen_conf={})
     if msg.find("ERROR: ") == 0:
         logging.error(
-            "'{}' dosen't work. {}".format(
+            "'{}' doesn't work. {}".format(
                 tenant["llm_id"],
                 msg))
     embd_mdl = LLMBundle(tenant["id"], LLMType.EMBEDDING, tenant["embd_id"])
     v, c = embd_mdl.encode(["Hello!"])
     if c == 0:
         logging.error(
-            "'{}' dosen't work!".format(
+            "'{}' doesn't work!".format(
                 tenant["embd_id"]))
 
 

api/db/services/canvas_service.py

@@ -73,11 +73,11 @@ class UserCanvasService(CommonService):
                 User.nickname,
                 User.avatar.alias('tenant_avatar'),
             ]
-            angents = cls.model.select(*fields) \
+            agents = cls.model.select(*fields) \
             .join(User, on=(cls.model.user_id == User.id)) \
             .where(cls.model.id == pid)
             # obj = cls.model.query(id=pid)[0]
-            return True, angents.dicts()[0]
+            return True, agents.dicts()[0]
         except Exception as e:
             print(e)
             return False, None
@@ -100,25 +100,25 @@ class UserCanvasService(CommonService):
             cls.model.update_time
         ]
         if keywords:
-            angents = cls.model.select(*fields).join(User, on=(cls.model.user_id == User.id)).where(
+            agents = cls.model.select(*fields).join(User, on=(cls.model.user_id == User.id)).where(
                 ((cls.model.user_id.in_(joined_tenant_ids) & (cls.model.permission == 
                                                                 TenantPermission.TEAM.value)) | (
                     cls.model.user_id == user_id)),
                 (fn.LOWER(cls.model.title).contains(keywords.lower()))
             )
         else:
-            angents = cls.model.select(*fields).join(User, on=(cls.model.user_id == User.id)).where(
+            agents = cls.model.select(*fields).join(User, on=(cls.model.user_id == User.id)).where(
                 ((cls.model.user_id.in_(joined_tenant_ids) & (cls.model.permission == 
                                                                 TenantPermission.TEAM.value)) | (
                     cls.model.user_id == user_id))
             )
         if desc:
-            angents = angents.order_by(cls.model.getter_by(orderby).desc())
+            agents = agents.order_by(cls.model.getter_by(orderby).desc())
         else:
-            angents = angents.order_by(cls.model.getter_by(orderby).asc())
-        count = angents.count()
-        angents = angents.paginate(page_number, items_per_page)
-        return list(angents.dicts()), count
+            agents = agents.order_by(cls.model.getter_by(orderby).asc())
+        count = agents.count()
+        agents = agents.paginate(page_number, items_per_page)
+        return list(agents.dicts()), count
    
 
 def completion(tenant_id, agent_id, question, session_id=None, stream=True, **kwargs):

api/ragflow_server.py

@@ -18,9 +18,9 @@
 # from beartype.claw import beartype_all  # <-- you didn't sign up for this
 # beartype_all(conf=BeartypeConf(violation_type=UserWarning))    # <-- emit warnings from all code
 
-from api.utils.log_utils import initRootLogger
+from api.utils.log_utils import init_root_logger
 from plugin import GlobalPluginManager
-initRootLogger("ragflow_server")
+init_root_logger("ragflow_server")
 
 import logging
 import os

api/utils/file_utils.py

@@ -158,7 +158,7 @@ def filename_type(filename):
     if re.match(r".*\.(eml|doc|docx|ppt|pptx|yml|xml|htm|json|csv|txt|ini|xls|xlsx|wps|rtf|hlp|pages|numbers|key|md|py|js|java|c|cpp|h|php|go|ts|sh|cs|kt|html|sql)$", filename):
         return FileType.DOC.value
 
-    if re.match(r".*\.(wav|flac|ape|alac|wavpack|wv|mp3|aac|ogg|vorbis|opus|mp3)$", filename):
+    if re.match(r".*\.(wav|flac|ape|alac|wavpack|wv|mp3|aac|ogg|vorbis|opus)$", filename):
         return FileType.AURAL.value
 
     if re.match(r".*\.(jpg|jpeg|png|tif|gif|pcx|tga|exif|fpx|svg|psd|cdr|pcd|dxf|ufo|eps|ai|raw|WMF|webp|avif|apng|icon|ico|mpg|mpeg|avi|rm|rmvb|mov|wmv|asf|dat|asx|wvx|mpe|mpa|mp4)$", filename):

api/utils/log_utils.py

@@ -30,7 +30,7 @@ def get_project_base_directory():
     )
     return PROJECT_BASE
 
-def initRootLogger(logfile_basename: str, log_format: str = "%(asctime)-15s %(levelname)-8s %(process)d %(message)s"):
+def init_root_logger(logfile_basename: str, log_format: str = "%(asctime)-15s %(levelname)-8s %(process)d %(message)s"):
     global initialized_root_logger
     if initialized_root_logger:
         return

api/utils/t_crypt.py

@@ -35,6 +35,6 @@ def crypt(line):
 
 
 if __name__ == "__main__":
-    pswd = crypt(sys.argv[1])
-    print(pswd)
-    print(decrypt(pswd))
+    passwd = crypt(sys.argv[1])
+    print(passwd)
+    print(decrypt(passwd))

api/utils/validation_utils.py

@@ -312,7 +312,7 @@ class PermissionEnum(StrEnum):
     team = auto()
 
 
-class ChunkMethodnEnum(StrEnum):
+class ChunkMethodEnum(StrEnum):
     naive = auto()
     book = auto()
     email = auto()
@@ -382,7 +382,7 @@ class CreateDatasetReq(Base):
     description: str | None = Field(default=None, max_length=65535)
     embedding_model: Annotated[str, StringConstraints(strip_whitespace=True, max_length=255), Field(default="", serialization_alias="embd_id")]
     permission: PermissionEnum = Field(default=PermissionEnum.me, min_length=1, max_length=16)
-    chunk_method: ChunkMethodnEnum = Field(default=ChunkMethodnEnum.naive, min_length=1, max_length=32, serialization_alias="parser_id")
+    chunk_method: ChunkMethodEnum = Field(default=ChunkMethodEnum.naive, min_length=1, max_length=32, serialization_alias="parser_id")
     parser_config: ParserConfig | None = Field(default=None)
 
     @field_validator("avatar")

deepdoc/parser/docx_parser.py

@@ -69,7 +69,7 @@ class RAGFlowDocxParser:
         max_type = max(max_type.items(), key=lambda x: x[1])[0]
 
         colnm = len(df.iloc[0, :])
-        hdrows = [0]  # header is not nessesarily appear in the first line
+        hdrows = [0]  # header is not necessarily appear in the first line
         if max_type == "Nu":
             for r in range(1, len(df)):
                 tys = Counter([blockType(str(df.iloc[r, j]))

deepdoc/parser/figure_parser.py

@@ -21,7 +21,7 @@ from rag.app.picture import vision_llm_chunk as picture_vision_llm_chunk
 from rag.prompts import vision_llm_figure_describe_prompt
 
 
-def vision_figure_parser_figure_data_wraper(figures_data_without_positions):
+def vision_figure_parser_figure_data_wrapper(figures_data_without_positions):
     return [
         (
             (figure_data[1], [figure_data[0]]),

deepdoc/parser/pdf_parser.py

@@ -180,13 +180,13 @@ class RAGFlowPdfParser:
         return fea
 
     @staticmethod
-    def sort_X_by_page(arr, threashold):
+    def sort_X_by_page(arr, threshold):
         # sort using y1 first and then x1
         arr = sorted(arr, key=lambda r: (r["page_number"], r["x0"], r["top"]))
         for i in range(len(arr) - 1):
             for j in range(i, -1, -1):
                 # restore the order using th
-                if abs(arr[j + 1]["x0"] - arr[j]["x0"]) < threashold \
+                if abs(arr[j + 1]["x0"] - arr[j]["x0"]) < threshold \
                         and arr[j + 1]["top"] < arr[j]["top"] \
                         and arr[j + 1]["page_number"] == arr[j]["page_number"]:
                     tmp = arr[j]
@@ -264,13 +264,13 @@ class RAGFlowPdfParser:
         for b in self.boxes:
             if b.get("layout_type", "") != "table":
                 continue
-            ii = Recognizer.find_overlapped_with_threashold(b, rows, thr=0.3)
+            ii = Recognizer.find_overlapped_with_threshold(b, rows, thr=0.3)
             if ii is not None:
                 b["R"] = ii
                 b["R_top"] = rows[ii]["top"]
                 b["R_bott"] = rows[ii]["bottom"]
 
-            ii = Recognizer.find_overlapped_with_threashold(
+            ii = Recognizer.find_overlapped_with_threshold(
                 b, headers, thr=0.3)
             if ii is not None:
                 b["H_top"] = headers[ii]["top"]
@@ -285,7 +285,7 @@ class RAGFlowPdfParser:
                 b["C_left"] = clmns[ii]["x0"]
                 b["C_right"] = clmns[ii]["x1"]
 
-            ii = Recognizer.find_overlapped_with_threashold(b, spans, thr=0.3)
+            ii = Recognizer.find_overlapped_with_threshold(b, spans, thr=0.3)
             if ii is not None:
                 b["H_top"] = spans[ii]["top"]
                 b["H_bott"] = spans[ii]["bottom"]

deepdoc/vision/layout_recognizer.py

@@ -106,7 +106,7 @@ class LayoutRecognizer(Recognizer):
                         bxs.pop(i)
                         continue
 
-                    ii = self.find_overlapped_with_threashold(bxs[i], lts_,
+                    ii = self.find_overlapped_with_threshold(bxs[i], lts_,
                                                               thr=0.4)
                     if ii is None:  # belong to nothing
                         bxs[i]["layout_type"] = ""

deepdoc/vision/recognizer.py

@@ -52,20 +52,20 @@ class Recognizer:
         self.label_list = label_list
 
     @staticmethod
-    def sort_Y_firstly(arr, threashold):
+    def sort_Y_firstly(arr, threshold):
         def cmp(c1, c2):
             diff = c1["top"] - c2["top"]
-            if abs(diff) < threashold:
+            if abs(diff) < threshold:
                 diff = c1["x0"] - c2["x0"]
             return diff
         arr = sorted(arr, key=cmp_to_key(cmp))
         return arr
 
     @staticmethod
-    def sort_X_firstly(arr, threashold):
+    def sort_X_firstly(arr, threshold):
         def cmp(c1, c2):
             diff = c1["x0"] - c2["x0"]
-            if abs(diff) < threashold:
+            if abs(diff) < threshold:
                 diff = c1["top"] - c2["top"]
             return diff
         arr = sorted(arr, key=cmp_to_key(cmp))
@@ -239,15 +239,15 @@ class Recognizer:
                 e -= 1
             break
 
-        max_overlaped_i, max_overlaped = None, 0
+        max_overlapped_i, max_overlapped = None, 0
         for i in range(s, e):
             ov = Recognizer.overlapped_area(bxs[i], box)
-            if ov <= max_overlaped:
+            if ov <= max_overlapped:
                 continue
-            max_overlaped_i = i
-            max_overlaped = ov
+            max_overlapped_i = i
+            max_overlapped = ov
 
-        return max_overlaped_i
+        return max_overlapped_i
 
     @staticmethod
     def find_horizontally_tightest_fit(box, boxes):
@@ -264,7 +264,7 @@ class Recognizer:
         return min_i
 
     @staticmethod
-    def find_overlapped_with_threashold(box, boxes, thr=0.3):
+    def find_overlapped_with_threshold(box, boxes, thr=0.3):
         if not boxes:
             return
         max_overlapped_i, max_overlapped, _max_overlapped = None, thr, 0

deepdoc/vision/t_recognizer.py

@@ -84,13 +84,13 @@ def get_table_html(img, tb_cpns, ocr):
     clmns = LayoutRecognizer.layouts_cleanup(boxes, clmns, 5, 0.5)
 
     for b in boxes:
-        ii = LayoutRecognizer.find_overlapped_with_threashold(b, rows, thr=0.3)
+        ii = LayoutRecognizer.find_overlapped_with_threshold(b, rows, thr=0.3)
         if ii is not None:
             b["R"] = ii
             b["R_top"] = rows[ii]["top"]
             b["R_bott"] = rows[ii]["bottom"]
 
-        ii = LayoutRecognizer.find_overlapped_with_threashold(b, headers, thr=0.3)
+        ii = LayoutRecognizer.find_overlapped_with_threshold(b, headers, thr=0.3)
         if ii is not None:
             b["H_top"] = headers[ii]["top"]
             b["H_bott"] = headers[ii]["bottom"]
@@ -104,7 +104,7 @@ def get_table_html(img, tb_cpns, ocr):
             b["C_left"] = clmns[ii]["x0"]
             b["C_right"] = clmns[ii]["x1"]
 
-        ii = LayoutRecognizer.find_overlapped_with_threashold(b, spans, thr=0.3)
+        ii = LayoutRecognizer.find_overlapped_with_threshold(b, spans, thr=0.3)
         if ii is not None:
             b["H_top"] = spans[ii]["top"]
             b["H_bott"] = spans[ii]["bottom"]

rag/app/naive.py

@@ -29,7 +29,7 @@ from tika import parser
 from api.db import LLMType
 from api.db.services.llm_service import LLMBundle
 from deepdoc.parser import DocxParser, ExcelParser, HtmlParser, JsonParser, MarkdownParser, PdfParser, TxtParser
-from deepdoc.parser.figure_parser import VisionFigureParser, vision_figure_parser_figure_data_wraper
+from deepdoc.parser.figure_parser import VisionFigureParser, vision_figure_parser_figure_data_wrapper
 from deepdoc.parser.pdf_parser import PlainParser, VisionParser
 from rag.nlp import concat_img, find_codec, naive_merge, naive_merge_with_images, naive_merge_docx, rag_tokenizer, tokenize_chunks, tokenize_chunks_with_images, tokenize_table
 
@@ -379,7 +379,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
         sections, tables = Docx()(filename, binary)
 
         if vision_model:
-            figures_data = vision_figure_parser_figure_data_wraper(sections)
+            figures_data = vision_figure_parser_figure_data_wrapper(sections)
             try:
                 docx_vision_parser = VisionFigureParser(vision_model=vision_model, figures_data=figures_data, **kwargs)
                 boosted_figures = docx_vision_parser(callback=callback)

rag/svr/task_executor.py

@@ -21,7 +21,7 @@ import sys
 import threading
 import time
 
-from api.utils.log_utils import initRootLogger, get_project_base_directory
+from api.utils.log_utils import init_root_logger, get_project_base_directory
 from graphrag.general.index import run_graphrag
 from graphrag.utils import get_llm_cache, set_llm_cache, get_tags_from_cache, set_tags_to_cache
 from rag.prompts import keyword_extraction, question_proposal, content_tagging
@@ -773,5 +773,5 @@ async def main():
 
 if __name__ == "__main__":
     faulthandler.enable()
-    initRootLogger(CONSUMER_NAME)
+    init_root_logger(CONSUMER_NAME)
     trio.run(main)