Come analizzare i moduli PDF con una macro ONLYOFFICE
30 aprile 2025Da Alice
Nel frenetico ambiente digitale di oggi, scrittori, redattori e creatori di contenuti spesso lottano per acquisire informazioni significative sui loro documenti. La comprensione di parametri come la leggibilità, la frequenza delle parole e l’equilibrio strutturale può migliorare significativamente la qualità dei documenti, ma l’analisi manuale richiede molto tempo e non è coerente. In questo post ti mostreremo come creare una potente macro ONLYOFFICE che analizza automaticamente i tuoi documenti e genera report completi.
Costruire la macro di analisi dei documenti
Scomponiamo la macro in componenti funzionali e spieghiamo il funzionamento di ciascuna parte.
Impostazione della funzione principale
Il cuore della nostra macro è la funzione analyzeDocument(), che orchestra l’intero processo di analisi:
function analyzeDocument() {
try {
// Get document and all text
var oDocument = Api.GetDocument();
var allText = "";
var paragraphs = oDocument.GetAllParagraphs();
// Check if document is empty
if (paragraphs.length === 0) {
console.log("Warning: Document is empty or no paragraphs found for analysis.");
return;
}
// Collect all text
paragraphs.forEach(function(paragraph) {
allText += paragraph.GetText() + " ";
});
// Perform analyses
var stats = calculateBasicStats(allText, paragraphs);
var advancedStats = calculateAdvancedStats(allText, stats);
var commonWords = findCommonWords(allText, 10);
// Create report
createAndAddReport(oDocument, stats, advancedStats, commonWords);
// Log success
console.log("Success: Document analysis completed. Report added to the end of the document.");
} catch (error) {
console.log("Error: " + error.message);
}
}
Questa funzione raccoglie prima tutto il testo dal documento, poi lo passa a funzioni di analisi specializzate e infine crea un report. Il blocco try-catch assicura che la macro gestisca con precisione eventuali errori.
Calcolo delle statistiche di base
La funzione calculateBasicStats() elabora il testo per estrarre le metriche fondamentali:
function calculateBasicStats(text, paragraphs) {
// Word count
var words = text.split(/\s+/).filter(function(word) {
return word.length > 0;
});
var wordCount = words.length;
// Sentence count
var sentences = text.split(/[.!?]+/).filter(function(sentence) {
return sentence.trim().length > 0;
});
var sentenceCount = sentences.length;
// Paragraph count
var paragraphCount = paragraphs.length;
// Character count
var charCountWithSpaces = text.length;
var charCountWithoutSpaces = text.replace(/\s+/g, "").length;
// Line count (approximate)
var lineCount = Math.ceil(charCountWithSpaces / 70);
return {
wordCount: wordCount,
sentenceCount: sentenceCount,
paragraphCount: paragraphCount,
charCountWithSpaces: charCountWithSpaces,
charCountWithoutSpaces: charCountWithoutSpaces,
lineCount: lineCount,
words: words,
sentences: sentences
};
}
Questa funzione divide il testo in parole e frasi, conta i paragrafi e calcola il numero di caratteri e di righe.
Esecuzione di analisi avanzate
Per ottenere informazioni più approfondite, la funzione calculateAdvancedStats() calcola metriche più sofisticate:
function calculateAdvancedStats(text, basicStats) {
// Average sentence length
var avgWordsPerSentence = basicStats.wordCount / Math.max(1, basicStats.sentenceCount);
// Average paragraph length
var avgWordsPerParagraph = basicStats.wordCount / Math.max(1, basicStats.paragraphCount);
// Average word length
var totalWordLength = basicStats.words.reduce(function(sum, word) {
return sum + word.length;
}, 0);
var avgWordLength = totalWordLength / Math.max(1, basicStats.wordCount);
// Readability score (simplified Flesch-Kincaid)
var readabilityScore = 206.835 - 1.015 * avgWordsPerSentence - 84.6 * (totalWordLength / basicStats.wordCount);
// Estimated reading time
var readingTimeMinutes = Math.ceil(basicStats.wordCount / 200);
return {
avgWordsPerSentence: avgWordsPerSentence,
avgWordsPerParagraph: avgWordsPerParagraph,
avgWordLength: avgWordLength,
readabilityScore: readabilityScore,
readingTimeMinutes: readingTimeMinutes
};
}
Calcola la lunghezza media di frasi e paragrafi, i punteggi di leggibilità e il tempo di lettura stimato.
Analisi della frequenza delle parole
La funzione findCommonWords() identifica le parole usate più frequentemente:
function findCommonWords(text, limit) {
// Clean text and convert to lowercase
var cleanText = text.toLowerCase().replace(/[.,\/#!$%\^&\*;:{}=\-_`~()]/g, "");
// Split into words
var words = cleanText.split(/\s+/).filter(function(word) {
return word.length > 3;
});
// Calculate word frequencies
var wordFrequency = {};
words.forEach(function(word) {
wordFrequency[word] = (wordFrequency[word] || 0) + 1;
});
// Filter stop words
var stopWords = ["this", "that", "with", "from", "have", "been"];
stopWords.forEach(function(stopWord) {
delete wordFrequency[stopWord];
});
// Sort by frequency
var sortedWords = Object.keys(wordFrequency).sort(function(a, b) {
return wordFrequency[b] - wordFrequency[a];
});
// Return top N words
return sortedWords.slice(0, limit).map(function(word) {
return { word: word, frequency: wordFrequency[word] };
});
}
function findCommonWords(text, limit) {
// Clean text and convert to lowercase
var cleanText = text.toLowerCase().replace(/[.,\/#!$%\^&\*;:{}=\-_`~()]/g, "");
// Split into words
var words = cleanText.split(/\s+/).filter(function(word) {
return word.length > 3;
});
// Calculate word frequencies
var wordFrequency = {};
words.forEach(function(word) {
wordFrequency[word] = (wordFrequency[word] || 0) + 1;
});
// Filter stop words
var stopWords = ["this", "that", "with", "from", "have", "been"];
stopWords.forEach(function(stopWord) {
delete wordFrequency[stopWord];
});
// Sort by frequency
var sortedWords = Object.keys(wordFrequency).sort(function(a, b) {
return wordFrequency[b] - wordFrequency[a];
});
// Return top N words
return sortedWords.slice(0, limit).map(function(word) {
return { word: word, frequency: wordFrequency[word] };
});
}
Questa funzione rimuove la punteggiatura, filtra le parole riempitive più comuni e restituisce le parole più frequentemente utilizzate nel documento.
Generazione del report
Infine, la funzione createAndAddReport() compila e formatta tutti i risultati dell’analisi:
function createAndAddReport(oDocument, basicStats, advancedStats, commonWords) {
// Add new page
var oParagraph = Api.CreateParagraph();
oParagraph.AddPageBreak();
oDocument.AddElement(oDocument.GetElementsCount(), oParagraph);
// Add title
var oHeading = Api.CreateParagraph();
oHeading.AddText("DOCUMENT ANALYSIS REPORT");
oDocument.AddElement(oDocument.GetElementsCount(), oHeading);
// Add basic statistics section
var oSubHeading = Api.CreateParagraph();
oSubHeading.AddText("BASIC STATISTICS");
oDocument.AddElement(oDocument.GetElementsCount(), oSubHeading);
// Add statistics content
// ... (code that adds individual statistics)
// Add advanced analysis section
// ... (code that adds advanced metrics)
// Add word frequency section
// ... (code that adds word frequency list)
// Add footer
var oFootnotePara = Api.CreateParagraph();
oFootnotePara.AddText("This report was generated by OnlyOffice Document Statistics and Analysis Tool on " +
new Date().toLocaleString() + ".");
oDocument.AddElement(oDocument.GetElementsCount(), oFootnotePara);
}
Questa funzione crea un report strutturato alla fine del documento con tutti i risultati dell’analisi.
Codice completo della macro
Ecco il codice completo della macro che puoi copiare e utilizzare:
(function() {
// Main function - starts all operations
function analyzeDocument() {
try {
// Get document and all text
var oDocument = Api.GetDocument();
var allText = "";
var paragraphs = oDocument.GetAllParagraphs();
// Check if document is empty
if (paragraphs.length === 0) {
console.log("Warning: Document is empty or no paragraphs found for analysis.");
return;
}
// Collect all text
paragraphs.forEach(function(paragraph) {
allText += paragraph.GetText() + " ";
});
// Calculate basic statistics
var stats = calculateBasicStats(allText, paragraphs);
// Perform advanced analysis
var advancedStats = calculateAdvancedStats(allText, stats);
// Find most common words
var commonWords = findCommonWords(allText, 10);
// Create and add report to the document
createAndAddReport(oDocument, stats, advancedStats, commonWords);
// Inform user
console.log("Success: Document analysis completed. Report added to the end of the document.");
} catch (error) {
console.log("Error: An error occurred during processing: " + error.message);
}
}
// Calculate basic statistics
function calculateBasicStats(text, paragraphs) {
// Word count
var words = text.split(/\s+/).filter(function(word) {
return word.length > 0;
});
var wordCount = words.length;
// Sentence count
var sentences = text.split(/[.!?]+/).filter(function(sentence) {
return sentence.trim().length > 0;
});
var sentenceCount = sentences.length;
// Paragraph count
var paragraphCount = paragraphs.length;
// Character count (with and without spaces)
var charCountWithSpaces = text.length;
var charCountWithoutSpaces = text.replace(/\s+/g, "").length;
// Line count (approximate)
var lineCount = Math.ceil(charCountWithSpaces / 70); // Approximately 70 characters/line
return {
wordCount: wordCount,
sentenceCount: sentenceCount,
paragraphCount: paragraphCount,
charCountWithSpaces: charCountWithSpaces,
charCountWithoutSpaces: charCountWithoutSpaces,
lineCount: lineCount,
words: words,
sentences: sentences
};
}
// Calculate advanced statistics
function calculateAdvancedStats(text, basicStats) {
// Average sentence length (in words)
var avgWordsPerSentence = basicStats.wordCount / Math.max(1, basicStats.sentenceCount);
// Average paragraph length (in words)
var avgWordsPerParagraph = basicStats.wordCount / Math.max(1, basicStats.paragraphCount);
// Average word length (in characters)
var totalWordLength = basicStats.words.reduce(function(sum, word) {
return sum + word.length;
}, 0);
var avgWordLength = totalWordLength / Math.max(1, basicStats.wordCount);
// Readability score (simplified Flesch-Kincaid)
var readabilityScore = 206.835 - 1.015 * (basicStats.wordCount / Math.max(1, basicStats.sentenceCount)) - 84.6 * (totalWordLength / Math.max(1, basicStats.wordCount));
// Estimated reading time (minutes)
var readingTimeMinutes = Math.ceil(basicStats.wordCount / 200); // Average reading speed 200 words/minute
return {
avgWordsPerSentence: avgWordsPerSentence,
avgWordsPerParagraph: avgWordsPerParagraph,
avgWordLength: avgWordLength,
readabilityScore: readabilityScore,
readingTimeMinutes: readingTimeMinutes
};
}
// Find most common words
function findCommonWords(text, limit) {
// Clean text and convert to lowercase
var cleanText = text.toLowerCase().replace(/[.,\/#!$%\^&\*;:{}=\-_`~()]/g, "");
// Split into words
var words = cleanText.split(/\s+/).filter(function(word) {
return word.length > 3; // Filter out very short words
});
// Calculate word frequencies
var wordFrequency = {};
words.forEach(function(word) {
if (wordFrequency[word]) {
wordFrequency[word]++;
} else {
wordFrequency[word] = 1;
}
});
// Filter stop words (common English words)
var stopWords = ["this", "that", "these", "those", "with", "from", "have", "been", "were", "they", "their", "what", "when", "where", "which", "there", "will", "would", "could", "should", "about", "also"];
stopWords.forEach(function(stopWord) {
if (wordFrequency[stopWord]) {
delete wordFrequency[stopWord];
}
});
// Sort by frequency
var sortedWords = Object.keys(wordFrequency).sort(function(a, b) {
return wordFrequency[b] - wordFrequency[a];
});
// Take top N words
var topWords = sortedWords.slice(0, limit);
// Return results as word-frequency pairs
return topWords.map(function(word) {
return {
word: word,
frequency: wordFrequency[word]
};
});
}
// Create and add report to document
function createAndAddReport(oDocument, basicStats, advancedStats, commonWords) {
// Add new page
var oParagraph = Api.CreateParagraph();
oParagraph.AddPageBreak();
oDocument.AddElement(oDocument.GetElementsCount(), oParagraph);
// Main title - highlighting in capital letters
var oHeading = Api.CreateParagraph();
oHeading.AddText("DOCUMENT ANALYSIS REPORT");
oDocument.AddElement(oDocument.GetElementsCount(), oHeading);
// Subheading - in capital letters
var oSubHeading = Api.CreateParagraph();
oSubHeading.AddText("BASIC STATISTICS");
oDocument.AddElement(oDocument.GetElementsCount(), oSubHeading);
// Add basic statistics
var oStatsPara = Api.CreateParagraph();
oStatsPara.AddText("• Word Count: " + basicStats.wordCount);
oDocument.AddElement(oDocument.GetElementsCount(), oStatsPara);
oStatsPara = Api.CreateParagraph();
oStatsPara.AddText("• Sentence Count: " + basicStats.sentenceCount);
oDocument.AddElement(oDocument.GetElementsCount(), oStatsPara);
oStatsPara = Api.CreateParagraph();
oStatsPara.AddText("• Paragraph Count: " + basicStats.paragraphCount);
oDocument.AddElement(oDocument.GetElementsCount(), oStatsPara);
oStatsPara = Api.CreateParagraph();
oStatsPara.AddText("• Character Count (with spaces): " + basicStats.charCountWithSpaces);
oDocument.AddElement(oDocument.GetElementsCount(), oStatsPara);
oStatsPara = Api.CreateParagraph();
oStatsPara.AddText("• Character Count (without spaces): " + basicStats.charCountWithoutSpaces);
oDocument.AddElement(oDocument.GetElementsCount(), oStatsPara);
oStatsPara = Api.CreateParagraph();
oStatsPara.AddText("• Estimated Line Count: " + basicStats.lineCount);
oDocument.AddElement(oDocument.GetElementsCount(), oStatsPara);
// Advanced analysis title
oSubHeading = Api.CreateParagraph();
oSubHeading.AddText("ADVANCED ANALYSIS");
oDocument.AddElement(oDocument.GetElementsCount(), oSubHeading);
// Add advanced analysis results
oStatsPara = Api.CreateParagraph();
oStatsPara.AddText("• Average Sentence Length: " + advancedStats.avgWordsPerSentence.toFixed(2) + " words");
oDocument.AddElement(oDocument.GetElementsCount(), oStatsPara);
oStatsPara = Api.CreateParagraph();
oStatsPara.AddText("• Average Paragraph Length: " + advancedStats.avgWordsPerParagraph.toFixed(2) + " words");
oDocument.AddElement(oDocument.GetElementsCount(), oStatsPara);
oStatsPara = Api.CreateParagraph();
oStatsPara.AddText("• Average Word Length: " + advancedStats.avgWordLength.toFixed(2) + " characters");
oDocument.AddElement(oDocument.GetElementsCount(), oStatsPara);
oStatsPara = Api.CreateParagraph();
oStatsPara.AddText("• Readability Score: " + advancedStats.readabilityScore.toFixed(2));
oDocument.AddElement(oDocument.GetElementsCount(), oStatsPara);
oStatsPara = Api.CreateParagraph();
oStatsPara.AddText("• Estimated Reading Time: " + advancedStats.readingTimeMinutes + " minutes");
oDocument.AddElement(oDocument.GetElementsCount(), oStatsPara);
// Common words title
oSubHeading = Api.CreateParagraph();
oSubHeading.AddText("MOST FREQUENTLY USED WORDS");
oDocument.AddElement(oDocument.GetElementsCount(), oSubHeading);
// We'll create a simple list instead of a table
if (commonWords.length > 0) {
for (var i = 0; i < commonWords.length; i++) {
var oWordPara = Api.CreateParagraph();
oWordPara.AddText((i + 1) + ". " + commonWords[i].word + " (" + commonWords[i].frequency + " times)");
oDocument.AddElement(oDocument.GetElementsCount(), oWordPara);
}
} else {
var oNoneFoundPara = Api.CreateParagraph();
oNoneFoundPara.AddText("No frequently used words found.");
oDocument.AddElement(oDocument.GetElementsCount(), oNoneFoundPara);
}
// Footer note
var oFootnotePara = Api.CreateParagraph();
oFootnotePara.AddText("This report was generated by OnlyOffice Document Statistics and Analysis Tool on " +
new Date().toLocaleString() + ".");
oDocument.AddElement(oDocument.GetElementsCount(), oFootnotePara);
}
// Run the macro
analyzeDocument();
})();
Per usare questa macro in ONLYOFFICE
- Apri il documento in ONLYOFFICE
- Passa alla scheda Visualizza e seleziona Macro
- Crea una nuova macro e incolla il codice
- Esegui la macro
- Alla fine del documento verrà aggiunto un rapporto di analisi dettagliato.
Ora eseguiamo la macro e vediamo come funziona!
Questa macro è uno strumento prezioso per i professionisti che desiderano automatizzare i processi di analisi del testo e di documentazione in un moderno ambiente d’ufficio. Ci auguriamo che sia un’utile aggiunta al tuo kit di strumenti di lavoro.
Ti invitiamo a esplorare la documentazione dell’API di ONLYOFFICE per creare le tue macro personalizzate o per migliorare questa macro. Se hai idee di miglioramento o suggerimenti per nuove macro, non esitare a contattarci. Il tuo feedback ci aiuta a continuare a sviluppare strumenti che rendono più efficiente la creazione e la modifica dei documenti.
Sull’autore
Crea il tuo account ONLYOFFICE gratuito
Visualizza, modifica e collabora su documenti, fogli, diapositive, moduli e file PDF online.
