File Filter Tool by Text Character Count

Filter files that meet the criteria from multiple document formats (TXT, PDF, DOCX, PPTX, etc.) based on the set Chinese character count range, and support packaged downloads.

Bug report

Browser execution mode: Your data is processed in your browser and is not uploaded to the server.

Speed and Stability: Processing speed depends on your device and browser. For large batch work, the desktop version may be more stable.

Loading tool, please wait...

If the online tool fails to load or run, try the desktop tool.https://tools.yikeaigc.com/

Tool Usage

Return to old version

Confirm word range, counting method, and parsing options in “Filter Settings” before starting. Files are read, counted, and packaged only on this page. For batch selection, the UI shows the first 20 files; all selected files are processed.

1Choose files or folder

Click to choose files, or drag documents here Supports TXT, SRT, HTML, Markdown, DOCX, PDF, PPTX, XLSX, and more. You can also select a folder for batch reading.

When selecting a folder, supported documents are read recursively. To keep the UI tidy, only the first 20 are previewed.

2Sample Data

Selected Files

Total Size

0 KB

Supported Formats

Preview Count

3File Preview

No files selected. You can load sample data first, then go to filter settings.

1Word Count Range

Min Words

Leave blank for no minimum.

Max Words

Leave blank for no maximum.

Filter Mode

The result ZIP includes only files matching the filter mode.

2Count Method

Chinese CharactersCounts only Chinese characters. Best for Chinese text length filters.

CJK CharactersCounts CJK range characters. Best for mixed-language documents.

Chinese & English WordsChinese by character; English and numbers by word segment.

Visible CharactersCounts non-whitespace characters. Best for character length filters.

3Parsing & Cleanup

Text Encoding

PDF Start Page

PDF only.

PDF End Page

Enter 0 to process to the last page.

Merge WhitespaceReduce line break and repeated space noise Ignore PunctuationApplies to visible characters and mixed count Full-width to Half-widthMakes numbers and English letters easier to count

Results
After filtering, download a ZIP of matching files or export the full stats report as CSV.

Waiting0%

Process Files

Matched

No Match

Parse Failed

1Filter Results

Not processed yet. Go to “Filter Settings” to confirm parameters, then start processing.

2Process Log

Waiting to start.

Instructions

Software Usage Instructions

Select files or folders: Click “Select Files” or “Select Folder”, or load the sample data directly. During batch import, the list only shows the first 20 files; the remaining files will be mentioned in the prompt, but all files will be included during processing.
Set parameters first: Switch to “Filter Settings” and confirm the word count range, counting method, encoding method, PDF page range, and whitespace and punctuation handling rules in order before continuing to the next step.
Start processing: After clicking “Start Processing”, the tool will read and count the file contents locally and will not upload them to the server.
View results: After processing is complete, view the matched items, misses, and parsing failure lists on the results page. You can also switch the display by result range.
Download output: Select the results you need and download them as ZIP or CSV. Result files will keep the original file names, and duplicate names will automatically have numbers appended for distinction.
Continue batch processing: Each step page provides a “Next” button, making it easy to quickly jump to the next settings page and process again.

FAQ

A: Common formats such as TXT, SRT, MD, HTML, HTM, DOCX, PDF, PPTX, XLSX, CSV, JSON, XML, and XLS are supported, as well as recursive folder reading.

A: You can enter an exact range, such as “300-1200”; you can also enter a single number, which means a range from 0 to that value, suitable for filtering short text or empty content.

A: If you mainly focus on Chinese content, choose Chinese character count; if the document contains mixed Chinese and English, choose mixed Chinese-English; if you care more about the content actually displayed on the page, choose the visible character method.

A: When a PDF is very long, you can count only a specified page range to avoid including the entire document. This is useful when you only need to check a specific section.

A: A number is automatically appended to the original file name to distinguish it. For example, files with the same name become “filename(2)” and “filename(3)”, preventing duplicates within the ZIP archive.

A: Common reasons include file corruption, nonstandard formatting, encoding issues, empty content, or a mismatch between the file type and its extension. You can try again with a sample in a similar format first.