Add get_txt function (#2639)

### What problem does this PR solve?

Add get_txt function to reduce duplicate code

### Type of change

- [x] Refactoring

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

deepdoc/parser/txt_parser.py

@@ -10,28 +10,18 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
+from deepdoc.parser.utils import get_txt
+from rag.nlp import num_tokens_from_string
 
-from rag.nlp import find_codec,num_tokens_from_string
-import re
 
 class RAGFlowTxtParser:
     def __call__(self, fnm, binary=None, chunk_token_num=128, delimiter="\n!?;。；！？"):
-        txt = ""
+        txt = get_txt(fnm, binary)
-        if binary:
-            encoding = find_codec(binary)
-            txt = binary.decode(encoding, errors="ignore")
-        else:
-            with open(fnm, "r") as f:
-                while True:
-                    l = f.readline()
-                    if not l:
-                        break
-                    txt += l
         return self.parser_txt(txt, chunk_token_num, delimiter)
 
     @classmethod
     def parser_txt(cls, txt, chunk_token_num=128, delimiter="\n!?;。；！？"):
-        if type(txt) != str:
+        if not isinstance(txt, str):
             raise TypeError("txt type should be str!")
         cks = [""]
         tk_nums = [0]

deepdoc/parser/utils.py

@@ -0,0 +1,29 @@
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+
+from rag.nlp import find_codec
+
+
+def get_txt(fnm: str, binary=None) -> str:
+    txt = ""
+    if binary:
+        encoding = find_codec(binary)
+        txt = binary.decode(encoding, errors="ignore")
+    else:
+        with open(fnm, "r") as f:
+            while True:
+                line = f.readline()
+                if not line:
+                    break
+                txt += line
+    return txt

rag/app/book.py

@@ -15,6 +15,7 @@ from tika import parser
 import re
 from io import BytesIO
 
+from deepdoc.parser.utils import get_text
 from rag.nlp import bullets_category, is_english, tokenize, remove_contents_table, \
     hierarchical_merge, make_colon_as_title, naive_merge, random_choices, tokenize_table, add_positions, \
     tokenize_chunks, find_codec
@@ -88,17 +89,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
 
     elif re.search(r"\.txt$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
-        txt = ""
+        txt = get_text(filename, binary)
-        if binary:
-            encoding = find_codec(binary)
-            txt = binary.decode(encoding, errors="ignore")
-        else:
-            with open(filename, "r") as f:
-                while True:
-                    l = f.readline()
-                    if not l:
-                        break
-                    txt += l
         sections = txt.split("\n")
         sections = [(l, "") for l in sections if l]
         remove_contents_table(sections, eng=is_english(

rag/app/laws.py

@@ -17,6 +17,7 @@ from io import BytesIO
 from docx import Document
 
 from api.db import ParserType
+from deepdoc.parser.utils import get_txt
 from rag.nlp import bullets_category, is_english, tokenize, remove_contents_table, hierarchical_merge, \
     make_colon_as_title, add_positions, tokenize_chunks, find_codec, docx_question_level
 from rag.nlp import rag_tokenizer
@@ -165,17 +166,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
 
     elif re.search(r"\.txt$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
-        txt = ""
+        txt = get_txt(filename, binary)
-        if binary:
-            encoding = find_codec(binary)
-            txt = binary.decode(encoding, errors="ignore")
-        else:
-            with open(filename, "r") as f:
-                while True:
-                    l = f.readline()
-                    if not l:
-                        break
-                    txt += l
         sections = txt.split("\n")
         sections = [l for l in sections if l]
         callback(0.8, "Finish parsing.")

rag/app/naive.py

@@ -169,7 +169,6 @@ class Markdown(MarkdownParser):
         return sections, tbls
 
 
-
 def chunk(filename, binary=None, from_page=0, to_page=100000,
           lang="Chinese", callback=None, **kwargs):
     """
@@ -190,7 +189,6 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
     doc["title_sm_tks"] = rag_tokenizer.fine_grained_tokenize(doc["title_tks"])
     res = []
     pdf_parser = None
-    sections = []
     if re.search(r"\.docx$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
         sections, tbls = Docx()(filename, binary)
@@ -222,13 +220,13 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
         callback(0.1, "Start to parse.")
         excel_parser = ExcelParser()
         if parser_config.get("html4excel"):
-            sections = [(l, "") for l in excel_parser.html(binary, 12) if l]
+            sections = [(_, "") for _ in excel_parser.html(binary, 12) if _]
         else:
-            sections = [(l, "") for l in excel_parser(binary) if l]
+            sections = [(_, "") for _ in excel_parser(binary) if _]
 
     elif re.search(r"\.(txt|py|js|java|c|cpp|h|php|go|ts|sh|cs|kt|sql)$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
-        sections = TxtParser()(filename,binary,
+        sections = TxtParser()(filename, binary,
                                parser_config.get("chunk_token_num", 128),
                                parser_config.get("delimiter", "\n!?;。；！？"))
         callback(0.8, "Finish parsing.")
@@ -242,13 +240,13 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
     elif re.search(r"\.(htm|html)$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
         sections = HtmlParser()(filename, binary)
-        sections = [(l, "") for l in sections if l]
+        sections = [(_, "") for _ in sections if _]
         callback(0.8, "Finish parsing.")
 
     elif re.search(r"\.json$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
         sections = JsonParser(int(parser_config.get("chunk_token_num", 128)))(binary)
-        sections = [(l, "") for l in sections if l]
+        sections = [(_, "") for _ in sections if _]
         callback(0.8, "Finish parsing.")
 
     elif re.search(r"\.doc$", filename, re.IGNORECASE):
@@ -256,7 +254,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
         binary = BytesIO(binary)
         doc_parsed = parser.from_buffer(binary)
         sections = doc_parsed['content'].split('\n')
-        sections = [(l, "") for l in sections if l]
+        sections = [(_, "") for _ in sections if _]
         callback(0.8, "Finish parsing.")
 
     else:

rag/app/one.py

@@ -13,6 +13,8 @@
 from tika import parser
 from io import BytesIO
 import re
+
+from deepdoc.parser.utils import get_txt
 from rag.app import laws
 from rag.nlp import rag_tokenizer, tokenize, find_codec
 from deepdoc.parser import PdfParser, ExcelParser, PlainParser, HtmlParser
@@ -82,17 +84,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
 
     elif re.search(r"\.(txt|md|markdown)$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
-        txt = ""
+        txt = get_txt(filename, binary)
-        if binary:
-            encoding = find_codec(binary)
-            txt = binary.decode(encoding, errors="ignore")
-        else:
-            with open(filename, "r") as f:
-                while True:
-                    l = f.readline()
-                    if not l:
-                        break
-                    txt += l
         sections = txt.split("\n")
         sections = [s for s in sections if s]
         callback(0.8, "Finish parsing.")

rag/app/qa.py

@@ -16,6 +16,8 @@ from io import BytesIO
 from timeit import default_timer as timer
 from nltk import word_tokenize
 from openpyxl import load_workbook
+
+from deepdoc.parser.utils import get_txt
 from rag.nlp import is_english, random_choices, find_codec, qbullets_category, add_positions, has_qbullet, docx_question_level
 from rag.nlp import rag_tokenizer, tokenize_table, concat_img
 from rag.settings import cron_logger
@@ -305,17 +307,7 @@ def chunk(filename, binary=None, lang="Chinese", callback=None, **kwargs):
         return res
     elif re.search(r"\.(txt|csv)$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
-        txt = ""
+        txt = get_txt(filename, binary)
-        if binary:
-            encoding = find_codec(binary)
-            txt = binary.decode(encoding, errors="ignore")
-        else:
-            with open(filename, "r") as f:
-                while True:
-                    l = f.readline()
-                    if not l:
-                        break
-                    txt += l
         lines = txt.split("\n")
         comma, tab = 0, 0
         for l in lines:
@@ -358,17 +350,7 @@ def chunk(filename, binary=None, lang="Chinese", callback=None, **kwargs):
         return res
     elif re.search(r"\.(md|markdown)$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
-        txt = ""
+        txt = get_txt(filename, binary)
-        if binary:
-            encoding = find_codec(binary)
-            txt = binary.decode(encoding, errors="ignore")
-        else:
-            with open(filename, "r") as f:
-                while True:
-                    l = f.readline()
-                    if not l:
-                        break
-                    txt += l
         lines = txt.split("\n")
         last_question, last_answer = "", ""
         question_stack, level_stack = [], []

rag/app/table.py

@@ -20,6 +20,7 @@ from openpyxl import load_workbook
 from dateutil.parser import parse as datetime_parse
 
 from api.db.services.knowledgebase_service import KnowledgebaseService
+from deepdoc.parser.utils import get_text
 from rag.nlp import rag_tokenizer, is_english, tokenize, find_codec
 from deepdoc.parser import ExcelParser
 
@@ -146,17 +147,7 @@ def chunk(filename, binary=None, from_page=0, to_page=10000000000,
             callback=callback)
     elif re.search(r"\.(txt|csv)$", filename, re.IGNORECASE):
         callback(0.1, "Start to parse.")
-        txt = ""
+        txt = get_text(filename, binary)
-        if binary:
-            encoding = find_codec(binary)
-            txt = binary.decode(encoding, errors="ignore")
-        else:
-            with open(filename, "r") as f:
-                while True:
-                    l = f.readline()
-                    if not l:
-                        break
-                    txt += l
         lines = txt.split("\n")
         fails = []
         headers = lines[0].split(kwargs.get("delimiter", "\t"))