Paragraph and Sentence Counter

Count text paragraphs, sentences, words, and characters, with support for batch processing and multiple formats

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

Set paragraph, sentence, and cleanup rules first, then enter text or select files to process. Use sample data to preview quickly.

Set up before processing No content added for counting yet.

1Choose input method

2Input text

Stats refresh in real time as you type; after processing, results are added to the list for export.

2Add Files

The UI shows the first 20 files; all selected files will be processed.

Click to choose files or drag them here

Supports .txt, .md, .docx, .pdf. DOCX and PDF text is extracted locally before counting.

2Load Example

Example data will replace current input or file list.

3Live Stats

Results update here automatically in direct input mode.

4Run Processing

Waiting to start.

No stats yet. Complete the steps before viewing.

Instructions

Software Usage Instructions

Set counting rules: First go to “Statistics Settings” and choose paragraph splitting, sentence splitting, word count mode, and report naming template.
Configure cleanup options:
- Paragraph splitting: Supports splitting by blank lines, one paragraph per line, and first-line indent detection.
- Sentence splitting: Supports splitting by sentence-ending punctuation, by line breaks, or by a combination of punctuation and line breaks.
- Text cleanup: Can normalize line breaks, trim leading and trailing whitespace, collapse multiple spaces, merge soft line breaks, remove HTML tags, and ignore content in brackets.
- Counting details: Can protect English abbreviations and decimal points, and choose whether to ignore punctuation in character counts.
Enter or select files:
- Direct input: Paste text to display paragraph, sentence, word, and character counts in real time.
- Batch files: Select TXT, MD, DOCX, or PDF files. The interface displays only the first 20 files, while the remaining files will also be processed.
- Sample data: Load Chinese manuscripts, mixed Chinese-English text, or batch text samples to quickly view the counting results.
Start processing: After confirming the settings and input content, click “Start Processing” and the tool will generate statistics according to the current rules.
View results: The results page shows paragraph count, sentence count, word count, character count, non-whitespace characters, average sentence length, average paragraph length, and processing status. Click a table row to view paragraph samples, sentence samples, and a text preview.
Export results: You can export a CSV summary or download a ZIP archive. The ZIP includes summary.csv, results.json, statistics notes, and per-file TXT reports.

FAQ

A: Split by blank lines is suitable for regular articles; one paragraph per line is suitable for lists and table-exported text; first-line indent detection is suitable for long manuscripts with relatively standardized formatting.

A: Sentence counting depends on punctuation, line breaks, and protection rules. When there are headings, numbering, abbreviations, decimal points, or special formatting, it is recommended to enable “Protect English abbreviations” and “Protect decimal points,” and switch the sentence splitting method according to the text type.

A: When copying text from PDFs, web pages, or layout software, unnatural line breaks may appear in the body text. After enabling “Merge soft line breaks,” the tool will try to merge consecutive body text lines to reduce cases where paragraphs are split apart.

A: TXT, MD, DOCX, and PDF are supported. DOCX files will have their body text extracted, and PDF files will read the text layer content. If the PDF is a scanned image, you need to run OCR recognition first before counting.

A: To keep the interface responsive, the file list only shows the first 20 for review. During actual processing, all selected files will be included, and the results will be fully written to CSV, JSON, and per-file reports.

A: Chinese by character + English by word is suitable for mixed Chinese-English text; split by whitespace is suitable for English or content that uses spaces to separate words; count Chinese characters only and count English words only are suitable for separately checking the quantity of a specific type of text.

A: The ZIP includes a summary.csv summary table, results.json structured data, statistics notes.txt, and per-file TXT reports in the reports directory. If “Include extracted text” is selected, it will also include the texts directory.