feta:

- add subcli xlsx2csv and csv2xlsx
- add categories and authors field in Cargo.toml

Cargo.toml

@@ -1,11 +1,13 @@
 [package]
 name = "xtab"
-version = "0.0.2"
+version = "0.0.3"
+authors = ["sharkLoc <[email protected]>"]
 edition = "2021"
 homepage = "https://github.com/sharkLoc/xtab"
 description = "xtab: CSV command line utilities"
 repository = "https://github.com/sharkLoc/xtab"
-keywords = ["csv"]
+keywords = ["csv","tsv"]
+categories = ["command-line-utilities"]
 readme = "README.md"
 license = "MIT"
 
@@ -15,11 +17,13 @@ license = "MIT"
 anyhow = "1.0.82"
 atty = "0.2.14"
 bzip2 = "0.4.4"
+calamine = "0.24.0"
 chrono = "0.4.38"
 clap = { version = "4.5.4", features = ["derive", "wrap_help"] }
 comfy-table = "7.1.1"
 csv = "1.3.0"
 env_logger = "0.10.0"
 flate2 = "1.0.28"
 log = "0.4.21"
+rust_xlsxwriter = "0.64.2"
 xz2 = "0.1.7"

README.md

@@ -23,7 +23,7 @@ cargo b --release
 
 ```bash
 xtab -- CSV command line utilities
-Version: 0.0.2
+Version: 0.0.3
 
 Authors: sharkLoc <[email protected]>
 Source code: https://github.com/sharkLoc/xtab.git
@@ -40,13 +40,15 @@ Usage: xtab [OPTIONS] [CSV] <COMMAND>
 
 Commands:
   addheader  Set new header for CSV file [aliases: ah]
+  csv2xlsx   Convert CSV/TSV files to XLSX file [aliases: c2x]
   dim        Dimensions of CSV file
   drop       Drop or Select CSV fields by columns index
   freq       freq
   head       Print first N records from CSV file
   pretty     Convert CSV to a readable aligned table
   tail       Print last N records from CSV file
   uniq       Unique data with keys
+  xlsx2csv   Convert XLSX to CSV format [aliases: x2c]
   view       Show CSV file content
   help       Print this message or the help of the given subcommand(s)
 

src/args.rs

@@ -6,21 +6,21 @@ use clap::{value_parser, Parser};
 #[command(
     name = "xtab",
     author = "sharkLoc",
-    version = "0.0.2",
+    version = "0.0.3",
     next_line_help = false,
-    about = "CSV command line utilities"
+    about = "CSV command line utilities",
+    long_about = "A simple and cross-platform program for CSV file manipulation"
 )]
 #[command(propagate_version = false, disable_help_flag = false, disable_version_flag = true)]
-#[command(long_about = "A simple and cross-platform program for CSV file manipulation")]
 #[command(before_help=r"xtab supports reading and writing gzip/bzip2/xz format file.
 Compression level:
   format   range   default   crate
   gzip     1-9     6         https://crates.io/crates/flate2
   bzip2    1-9     6         https://crates.io/crates/bzip2
   xz       1-9     6         https://crates.io/crates/xz2"
 )]
-#[command(help_template = "{name} -- {about}\nVersion: {version}\
-    \n\nAuthors: {author} <[email protected]>\
+#[command(help_template = "{name} -- {about}\n\nVersion: {version}\
+    \nAuthors: {author} <[email protected]>\
     \nSource code: https://github.com/sharkLoc/xtab.git\
     \n\n{before-help}
 {usage-heading} {usage}\n\n{all-args}\n\nUse \"xtab help [command]\" for more information about a command")]
@@ -78,6 +78,19 @@ pub enum Cmd {
         output: Option<PathBuf>,
     },
 
+    /// Convert CSV/TSV files to XLSX file
+    #[command(visible_alias = "c2x")]
+    csv2xlsx {
+        /// If set, bold first line in XLSX file
+        #[arg(short = 'B', long = "bold-first", help_heading = Some("FLAGS"))]
+        bold: bool,
+        /// If set, border first line in XLSX file
+        #[arg(short = 'b', long = "border-first", help_heading = Some("FLAGS"))]
+        border: bool,
+        /// Output xlsx file name, e.g, result.xlsx
+        #[arg(short = 'x', long = "xlsx", value_name = "FILE", default_value_t = String::from("Sheet1.xlsx"))]
+        xlsx: String,
+    },
     /// Dimensions of CSV file
     dim {
         /// Output file name, file ending in .gz/.bz2/.xz will be compressed automatically, if file not specified write data to stdout
@@ -166,6 +179,20 @@ pub enum Cmd {
         output: Option<PathBuf>,
     },
 
+    /// Convert XLSX to CSV format
+    #[command(visible_alias = "x2c")]
+    xlsx2csv {
+        /// Input XLSX file
+        #[arg(value_name = "FILE")]
+        xlsx: Option<PathBuf>,
+        /// Select Nth sheet to retrieve
+        #[arg(short = 'i', long = "sheet-index", value_name = "INT", default_value_t=1)]
+        idx: usize,
+        /// Output file name, file ending in .gz/.bz2/.xz will be compressed automatically, if file not specified write data to stdout
+        #[arg(short = 'o', long = "out-csv", value_name = "FILE")]
+        csv: Option<PathBuf>,
+    },
+
     /// Show CSV file content
     view {
         /// Skip first N records, not include the header row when option "--no-header" enabled. eg "-s 10 --no-header" will skip 11 records

src/command/csv2xlsx.rs

@@ -0,0 +1,52 @@
+use crate::utils::*;
+use anyhow::{Error, Ok};
+use csv::ReaderBuilder;
+use log::info;
+use rust_xlsxwriter::{Format, FormatBorder, Workbook};
+use std::{path::PathBuf, time::Instant};
+
+pub fn csv_xlsx(
+    no_header: bool,
+    delimiter: u8,
+    bold_first: bool,
+    border_first: bool,
+    csv: Option<PathBuf>,
+    xlsx: &str,
+) -> Result<(), Error> {
+    let start = Instant::now();
+
+    let mut csv_reader = ReaderBuilder::new()
+        .has_headers(no_header)
+        .flexible(true)
+        .delimiter(delimiter)
+        .from_reader(file_reader(csv.as_ref())?);
+
+    match csv {
+        Some(csv) => info!("read file from: {:?}", csv),
+        None => info!("read file from stdin "),
+    }
+
+    let mut work_book = Workbook::new();
+    let work_sheet = work_book.add_worksheet();
+
+    let format = match (bold_first, border_first) {
+        (true, true) => Format::new().set_bold().set_border(FormatBorder::Double),
+        (false, false) => Format::new(),
+        (true, false) => Format::new().set_bold(),
+        (false, true) => Format::new().set_border(FormatBorder::Double),
+    };
+
+    for (nrow, rec) in csv_reader.records().flatten().enumerate() {
+        for (ncol, cell) in rec.iter().enumerate() {
+            if (bold_first || border_first) && nrow == 0 {
+                work_sheet.write_with_format(nrow as u32, ncol as u16, cell, &format)?;
+            } else {
+                work_sheet.write(nrow as u32, ncol as u16, cell)?;
+            }
+        }
+    }
+    work_book.save(xlsx)?;
+
+    info!("time elapsed is: {:?}", start.elapsed());
+    Ok(())
+}

src/command/drop.rs

@@ -31,7 +31,7 @@ pub fn drop_csv(
     for idx in index_str.split(',').collect::<Vec<&str>>() {
         let idx = idx.parse::<usize>()?;
         if col_index.contains(&idx) {
-            warn!("duplicate columns index {}, keep first one",idx);
+            warn!("duplicate columns index {}, keep first one", idx);
             continue;
         } else {
             col_index.push(idx);
@@ -49,13 +49,13 @@ pub fn drop_csv(
 
     for rec in csv_reader.records().flatten() {
         let mut rec_new = StringRecord::new();
-        for (idx,each) in rec.iter().enumerate() {
+        for (idx, each) in rec.iter().enumerate() {
             if invert {
-                if col_index.contains(&(idx+1)) {
+                if col_index.contains(&(idx + 1)) {
                     rec_new.push_field(each);
                 }
             } else {
-                if !col_index.contains(&(idx+1)) {
+                if !col_index.contains(&(idx + 1)) {
                     rec_new.push_field(each);
                 }
             }