rasgapdf 0.1.1

Blazing-fast spatial 2D PDF parser in pure Rust with multi-language bindings (Python, Node.js, Go, C#)
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227

use std::fs::File;
use std::io::Write;
use clap::{Parser, ValueEnum};
use rasgapdf::{parse_file, parse_raw_file, ParserOptions};

#[derive(ValueEnum, Clone, Copy, Debug, PartialEq, Eq)]
pub enum OutputFormat {
    Json,
    Text,
    Csv,
    Tsv,
}

#[derive(Parser, Debug)]
#[command(
    name = "rasgapdf",
    author = "Messias Martins",
    version = env!("CARGO_PKG_VERSION"),
    about = "⚡ Blazing-fast 2D Spatial PDF Parser in Pure Rust",
    long_about = "Extracts exact physical 2D coordinates (X/Y) or structured blocks/tables from PDF files at native hardware speeds."
)]
struct Cli {
    /// Caminho para o arquivo PDF
    #[arg(value_name = "PDF_FILE")]
    input: String,

    /// Ativar Modo Bruto: retorna exclusivamente a lista plana de coordenadas X/Y sem overhead de blocos/tabelas
    #[arg(short, long, default_value_t = false)]
    raw: bool,

    /// Formato de saída: json, text, csv, tsv (padrão: json)
    #[arg(short, long, value_enum, default_value_t = OutputFormat::Json)]
    format: OutputFormat,

    /// Arquivo de saída para salvar o resultado (padrão: stdout)
    #[arg(short, long, value_name = "OUTPUT_FILE")]
    output: Option<String>,

    /// Formatar JSON com identação legível
    #[arg(short, long, default_value_t = false)]
    pretty: bool,

    /// Desativar detector automático de tabelas (apenas no modo estruturado)
    #[arg(long, default_value_t = false)]
    no_tables: bool,

    /// Tolerância horizontal para agrupamento de colunas (em pontos)
    #[arg(long, default_value_t = 16.0)]
    col_tolerance: f32,

    /// Tolerância vertical para agrupamento de linhas (em pontos)
    #[arg(long, default_value_t = 6.0)]
    row_tolerance: f32,

    /// Quantidade mínima de colunas para considerar uma tabela
    #[arg(long, default_value_t = 3)]
    min_table_cols: usize,
}

fn main() -> Result<(), Box<dyn std::error::Error>> {
    let args = Cli::parse();

    if args.raw {
        // --- MODO 1: COORDENADAS BRUTAS (RAW X/Y) ---
        let raw_doc = match parse_raw_file(&args.input) {
            Ok(d) => d,
            Err(e) => {
                eprintln!("❌ Erro ao processar PDF (modo raw): {}", e);
                std::process::exit(1);
            }
        };

        let result_string = match args.format {
            OutputFormat::Json => {
                if args.pretty {
                    serde_json::to_string_pretty(&raw_doc)?
                } else {
                    serde_json::to_string(&raw_doc)?
                }
            }
            OutputFormat::Text => {
                let mut out = String::new();
                out.push_str(&format!(
                    "# RasgaPDF Raw Spatial Dump - Arquivo: {} | Páginas: {} | Spans: {} | Tempo: {:.2} ms\n",
                    raw_doc.file_name, raw_doc.total_pages, raw_doc.total_spans, raw_doc.parse_time_ms
                ));
                for s in &raw_doc.spans {
                    out.push_str(&format!(
                        "[Pág. {:2}] (X0: {:7.2}, Y0: {:7.2}, X1: {:7.2}, Y1: {:7.2}) [{:4.1}pt] {}\n",
                        s.page, s.x0, s.y0, s.x1, s.y1, s.font_size, s.text
                    ));
                }
                out
            }
            OutputFormat::Csv => {
                let mut out = String::from("page,x0,y0,x1,y1,font_size,font_name,text\n");
                for s in &raw_doc.spans {
                    let escaped_text = s.text.replace('"', "\"\"");
                    out.push_str(&format!(
                        "{},{:.2},{:.2},{:.2},{:.2},{:.1},\"{}\",\"{}\"\n",
                        s.page, s.x0, s.y0, s.x1, s.y1, s.font_size, s.font_name, escaped_text
                    ));
                }
                out
            }
            OutputFormat::Tsv => {
                let mut out = String::from("page\tx0\ty0\tx1\ty1\tfont_size\tfont_name\ttext\n");
                for s in &raw_doc.spans {
                    let sanitized = s.text.replace('\t', " ").replace('\n', " ");
                    out.push_str(&format!(
                        "{}\t{:.2}\t{:.2}\t{:.2}\t{:.2}\t{:.1}\t{}\t{}\n",
                        s.page, s.x0, s.y0, s.x1, s.y1, s.font_size, s.font_name, sanitized
                    ));
                }
                out
            }
        };

        if let Some(out_path) = args.output {
            let mut file = File::create(&out_path)?;
            file.write_all(result_string.as_bytes())?;
            eprintln!(
                "⚡ Extração bruta (raw X/Y) concluída em {:.2} ms ({} spans em {} páginas) -> Salvo em {}",
                raw_doc.parse_time_ms, raw_doc.total_spans, raw_doc.total_pages, out_path
            );
        } else {
            println!("{}", result_string);
            eprintln!(
                "⚡ Raw X/Y extraído em {:.2} ms | Total spans: {} | Páginas: {}",
                raw_doc.parse_time_ms, raw_doc.total_spans, raw_doc.total_pages
            );
        }
    } else {
        // --- MODO 2: ESTRUTURADO (HIERÁRQUICO COM BLOCOS E TABELAS) ---
        let options = ParserOptions {
            mode: "structured".to_string(),
            detect_tables: !args.no_tables,
            min_table_columns: args.min_table_cols,
            column_tolerance: args.col_tolerance,
            row_tolerance: args.row_tolerance,
        };

        let doc = match parse_file(&args.input, &options) {
            Ok(d) => d,
            Err(e) => {
                eprintln!("❌ Erro ao processar PDF: {}", e);
                std::process::exit(1);
            }
        };

        let result_string = match args.format {
            OutputFormat::Json => {
                if args.pretty {
                    serde_json::to_string_pretty(&doc)?
                } else {
                    serde_json::to_string(&doc)?
                }
            }
            OutputFormat::Text => {
                let mut out = String::new();
                out.push_str(&format!(
                    "# RasgaPDF Structured Dump - Arquivo: {} | Páginas: {} | Tempo: {:.2} ms\n",
                    doc.file_name, doc.total_pages, doc.parse_time_ms
                ));
                for page in &doc.pages {
                    out.push_str(&format!("\n=== Página {} ({}x{}) ===\n", page.page_number, page.width, page.height));
                    if !page.tables.is_empty() {
                        out.push_str(&format!("  [Tabelas Detectadas: {}]\n", page.tables.len()));
                        for (idx, tbl) in page.tables.iter().enumerate() {
                            out.push_str(&format!("    Tabela #{}: {} linhas x {} colunas (Bbox: {:?})\n", idx + 1, tbl.rows.len(), tbl.col_count, tbl.bbox));
                        }
                    }
                    out.push_str(&format!("  [Blocos de Texto: {}]\n", page.text_blocks.len()));
                    for block in &page.text_blocks {
                        out.push_str(&format!("    Bloco #{}: {:?}\n", block.block_id, block.bbox));
                        for line in &block.lines {
                            out.push_str(&format!("      Linha: {:?} -> \"{}\"\n", line.bbox, line.text));
                        }
                    }
                }
                out
            }
            OutputFormat::Csv | OutputFormat::Tsv => {
                eprintln!("⚠️ Formatos CSV e TSV diretos são recomendados no modo `--raw`. Alternando para listagem plana...");
                let raw_doc = parse_raw_file(&args.input).map_err(|e| e.to_string())?;
                if args.format == OutputFormat::Csv {
                    let mut out = String::from("page,x0,y0,x1,y1,font_size,font_name,text\n");
                    for s in &raw_doc.spans {
                        let escaped_text = s.text.replace('"', "\"\"");
                        out.push_str(&format!(
                            "{},{:.2},{:.2},{:.2},{:.2},{:.1},\"{}\",\"{}\"\n",
                            s.page, s.x0, s.y0, s.x1, s.y1, s.font_size, s.font_name, escaped_text
                        ));
                    }
                    out
                } else {
                    let mut out = String::from("page\tx0\ty0\tx1\ty1\tfont_size\tfont_name\ttext\n");
                    for s in &raw_doc.spans {
                        let sanitized = s.text.replace('\t', " ").replace('\n', " ");
                        out.push_str(&format!(
                            "{}\t{:.2}\t{:.2}\t{:.2}\t{:.2}\t{:.1}\t{}\t{}\n",
                            s.page, s.x0, s.y0, s.x1, s.y1, s.font_size, s.font_name, sanitized
                        ));
                    }
                    out
                }
            }
        };

        if let Some(out_path) = args.output {
            let mut file = File::create(&out_path)?;
            file.write_all(result_string.as_bytes())?;
            eprintln!(
                "✅ Extração estruturada concluída em {:.2} ms ({} páginas) -> Salvo em {}",
                doc.parse_time_ms, doc.total_pages, out_path
            );
        } else {
            println!("{}", result_string);
            eprintln!(
                "⚡ Estruturado em {:.2} ms | Páginas: {} | Arquivo: {}",
                doc.parse_time_ms, doc.total_pages, doc.file_name
            );
        }
    }

    Ok(())
}