reorganize lib code

Author: ribbondz

Cargo.lock

@@ -1,6 +1,6 @@
 [package]
 name = "csv-txt-excel-parallel-toolkit"
-version = "0.4.15"
+version = "0.4.16"
 edition = "2021"
 authors = ["zhuang dai <[email protected]>"]
 description = "A parallel and fast command line toolkit for small and large (>10G) CSV, TXT, and EXCEL files, with a unified api."

Cargo.toml

@@ -1,9 +1,5 @@
-use crate::utils::{
-    cli_result::E, file::is_excel, filename::full_path, row_split::CsvRowSplitter,
-    util::get_valid_sep,
-};
+use crate::utils::{row_split::CsvRowSplitter, util::get_valid_sep};
 use clap::Args;
-use std::path::PathBuf;
 
 #[derive(Debug, Args)]
 pub struct Count {
@@ -415,49 +411,6 @@ pub struct Unique {
     pub export: bool,
 }
 
-macro_rules! command_run {
-    ($method:ident) => {
-        impl $method {
-            pub fn path(&self) -> PathBuf {
-                let p = self.filename.as_ref().unwrap();
-                full_path(p)
-            }
-
-            pub fn run(&self) {
-                match &self.filename {
-                    Some(f) => match is_excel(&full_path(f)) {
-                        true => self.excel_run(),
-                        false => self.csv_run(),
-                    },
-                    None => self.io_run(),
-                }
-                .handle_err()
-            }
-        }
-    };
-}
-
-command_run!(Count);
-command_run!(Estimate);
-command_run!(Head);
-command_run!(Tail);
-command_run!(Headers);
-command_run!(Clean);
-command_run!(Flatten);
-command_run!(Frequency);
-command_run!(Split);
-command_run!(Slice);
-command_run!(Select);
-command_run!(Stats);
-command_run!(Excel2csv);
-command_run!(Table);
-command_run!(Sort);
-command_run!(Search);
-command_run!(Sample);
-command_run!(To);
-command_run!(Unique);
-command_run!(Size);
-
 macro_rules! impl_row_split {
     ($cmd:ident) => {
         impl $cmd {

src/args.rs

@@ -1,29 +1,22 @@
-use crate::args::Count;
 use crate::utils::return_result::{CliResultData, ResultData};
 use std::fs::File;
 use std::io::{BufRead, BufReader};
-use std::path::Path;
+use std::path::{Path, PathBuf};
 extern crate bytecount;
 
-impl Count {
-    #[allow(dead_code)]
-    pub fn csv_run_lib(&self) -> CliResultData {
-        let mut out = ResultData::new();
-
-        // current file
-        let n = match self.path().is_dir() {
-            true => count_dir_files(&self.path())?,
-            false => count_file_lines(&self.path(), self.no_header)?,
-        };
-
-        out.insert_header(vec!["count".to_string()]);
-        out.insert_record(vec![n.to_string()]);
-
-        Ok(Some(out))
-    }
+pub fn csv_count(file: &PathBuf, no_header: bool) -> CliResultData {
+    // current file
+    let n = match file.is_dir() {
+        true => count_dir_files(&file)?,
+        false => count_file_lines(&file, no_header)?,
+    };
+
+    Ok(Some(ResultData {
+        header: vec!["count".to_string()],
+        data: vec![vec![n.to_string()]],
+    }))
 }
 
-#[allow(dead_code)]
 fn count_file_lines(path: &Path, no_header: bool) -> Result<usize, Box<dyn std::error::Error>> {
     // open file and count
     let mut n = 0;
@@ -49,7 +42,6 @@ fn count_file_lines(path: &Path, no_header: bool) -> Result<usize, Box<dyn std::
     Ok(n)
 }
 
-#[allow(dead_code)]
 fn count_dir_files(path: &Path) -> Result<usize, Box<dyn std::error::Error>> {
     let mut file_n = 0;
     let mut dir_n = 0;

src/csv_lib/count.rs

@@ -1,34 +1,37 @@
-use crate::args::Head;
 use crate::utils::return_result::{CliResultData, ResultData};
+use crate::utils::row_split::CsvRowSplitter;
 use std::fs::File;
 use std::io::{BufRead, BufReader};
+use std::path::PathBuf;
 
-impl Head {
-    #[allow(dead_code)]
-    pub fn csv_run_lib(&self) -> CliResultData {
-        let mut out = ResultData::new();
-        let path = self.path();
+pub fn csv_head(
+    file: &PathBuf,
+    no_header: bool,
+    sep: char,
+    quote: char,
+    n: usize,
+) -> CliResultData {
+    let mut out = ResultData::new();
 
-        // show head n
-        let mut lines = BufReader::new(File::open(path)?)
-            .lines()
-            .take(self.n + 1 - self.no_header as usize);
+    // show head n
+    let mut lines = BufReader::new(File::open(file)?)
+        .lines()
+        .take(n + 1 - no_header as usize);
 
-        // Process header
-        if let Some(header) = lines.next() {
-            if let Ok(h) = header {
-                let h = self.split_row_to_owned_vec(&h);
-                out.insert_header(h);
-            }
+    // Process header
+    if let Some(header) = lines.next() {
+        if let Ok(h) = header {
+            let h = CsvRowSplitter::new(&h, sep, quote).collect_owned();
+            out.insert_header(h);
         }
+    }
 
-        lines.for_each(|r| {
-            if let Ok(r) = r {
-                let r = self.split_row_to_owned_vec(&r);
-                out.insert_record(r);
-            }
-        });
+    lines.for_each(|r| {
+        if let Ok(r) = r {
+            let r = CsvRowSplitter::new(&r, sep, quote).collect_owned();
+            out.insert_record(r);
+        }
+    });
 
-        Ok(Some(out))
-    }
+    Ok(Some(out))
 }

src/csv_lib/head.rs

@@ -1,22 +1,19 @@
-use crate::args::Headers;
 use crate::utils::return_result::{CliResultData, ResultData};
+use crate::utils::row_split::CsvRowSplitter;
 use std::fs::File;
 use std::io::{BufRead, BufReader};
+use std::path::PathBuf;
 
-impl Headers {
-    #[allow(dead_code)]
-    pub fn csv_run_lib(&self) -> CliResultData {
-        let mut out = ResultData::new();
+pub fn csv_headers(file: &PathBuf, sep: char, quote: char) -> CliResultData {
+    let mut out = ResultData::new();
 
-        // open file and header
-        let mut rdr = BufReader::new(File::open(self.path())?).lines();
+    // open file and header
+    let mut rdr = BufReader::new(File::open(&file)?).lines();
 
-        out.insert_header(vec!["column_name".to_string()]);
-        if let Some(r) = rdr.next() {
-            self.split(&r?)
-                .for_each(|v| out.insert_record(vec![v.to_string()]));
-        };
+    out.insert_header(vec!["column_name".to_string()]);
+    if let Some(r) = rdr.next() {
+        CsvRowSplitter::new(&r?, sep, quote).for_each(|v| out.insert_record(vec![v.to_string()]));
+    };
 
-        Ok(Some(out))
-    }
+    Ok(Some(out))
 }

src/csv_lib/headers.rs

@@ -1,4 +1,3 @@
 pub mod count;
 pub mod head;
 pub mod headers;
-pub mod size;

src/csv_lib/mod.rs

@@ -1,7 +1,7 @@
 use crate::args::Sort;
 use crate::utils::cli_result::CliResult;
 use crate::utils::constants::COMMA;
-use crate::utils::excel::datatype_vec_to_string_vec;
+use crate::utils::excel::datatype_vec_to_str_vec;
 use crate::utils::filename::new_path;
 use crate::utils::reader::ExcelReader;
 use crate::utils::sort::SortColumns;
@@ -29,7 +29,7 @@ impl Sort {
         let mut lines = range
             .iter()
             .skip(range.next_called)
-            .map(datatype_vec_to_string_vec)
+            .map(datatype_vec_to_str_vec)
             .collect::<Vec<_>>();
 
         // sort

src/csv_lib/size.rs

@@ -0,0 +1,20 @@
+use crate::utils::reader::ExcelReader;
+use crate::utils::return_result::{CliResultData, ResultData};
+use std::path::PathBuf;
+extern crate bytecount;
+
+pub fn excel_count(file: &PathBuf, no_header: bool, sheet: usize) -> CliResultData {
+    // open file and count
+    let range = ExcelReader::new(&file, sheet)?;
+    let mut n = range.len();
+
+    // default to have a header
+    if !no_header && n > 0 {
+        n -= 1;
+    }
+
+    Ok(Some(ResultData {
+        header: vec!["count".to_string()],
+        data: vec![vec![n.to_string()]],
+    }))
+}