Enhancing file parsing (#2)

## Changes
* Ignoring numerical and special characters during parsing

Reviewed-on: #2
Co-authored-by: kdeng00 <kundeng94@gmail.com>
Co-committed-by: kdeng00 <kundeng94@gmail.com>
This commit is contained in:
kdeng00
2024-06-15 16:19:10 +00:00
committed by phoenix
parent 7cc9ded225
commit 095da0e04c
3 changed files with 48 additions and 39 deletions
+3 -6
View File
@@ -1,13 +1,10 @@
[package] [package]
name = "clean_file" name = "clean_file"
version = "0.1.0" version = "0.2.0"
edition = "2021" edition = "2021"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies] [dependencies]
serde = { version = "1.0.188", features = ["derive"] } serde = { version = "1.0.203", features = ["derive"] }
serde_json = "1.0.117"
# serde = { version = "1.0", features = ["derive"] }
serde_json = "1.0"
+13 -10
View File
@@ -14,23 +14,26 @@ fn main() {
println!("Filepath is: {:?}", filepath); println!("Filepath is: {:?}", filepath);
let myparser = parser::parser::NumberParser let myparser = parser::parser::NumberParser {
{ filepath: filepath.clone(),
filepath: filepath.clone()
}; };
println!("\nDumping files");
let rawvalues = myparser.filedump(); let rawvalues = myparser.filedump();
println!("\nUpdating values");
let parsed_values = myparser.updatevalues(&rawvalues); let parsed_values = myparser.updatevalues(&rawvalues);
println!("\nRemoving duplicates");
let newupdated = myparser.removedups(&parsed_values); let newupdated = myparser.removedups(&parsed_values);
println!("\nPrinting values"); myparser.print_values(&newupdated, true);
myparser.print_values(&newupdated);
println!("\nSaving file"); let result = myparser.save_file(parsed_values);
let _result = myparser.save_file(parsed_values);
match result {
Ok(o) => {
println!("Successfully saved file: {:?}", o);
}
Err(er) => {
println!("Error saving file: {:?}", er);
}
}
} }
+31 -22
View File
@@ -1,25 +1,24 @@
pub mod parser { pub mod parser {
use std::collections::HashSet; use std::collections::HashSet;
use std::fs::File; use std::fs::File;
use std::io::{BufRead, BufReader};
use std::io::prelude::*; use std::io::prelude::*;
use std::io::{BufRead, BufReader};
use serde::Deserialize; use serde::Deserialize;
use serde::Serialize; use serde::Serialize;
#[derive(Clone, Deserialize, Serialize)] #[derive(Clone, Deserialize, Serialize)]
pub struct SomeObject { pub struct SomeObject {
pub value: String pub value: String,
} }
pub struct NumberParser { pub struct NumberParser {
pub filepath: String pub filepath: String,
} }
impl NumberParser { impl NumberParser {
pub fn filedump(&self) -> Vec<SomeObject> { pub fn filedump(&self) -> Vec<SomeObject> {
println!("\nDumping files");
let mut objs: Vec<SomeObject> = Vec::new(); let mut objs: Vec<SomeObject> = Vec::new();
if let Ok(lines) = self.read_lines(&self.filepath) { if let Ok(lines) = self.read_lines(&self.filepath) {
@@ -31,9 +30,7 @@ pub mod parser {
continue; continue;
} }
let myobj: SomeObject = SomeObject { let myobj: SomeObject = SomeObject { value: phonenumber };
value: phonenumber
};
if !myobj.value.is_empty() { if !myobj.value.is_empty() {
objs.push(myobj); objs.push(myobj);
@@ -46,6 +43,7 @@ pub mod parser {
} }
pub fn updatevalues(&self, vals: &Vec<SomeObject>) -> Vec<SomeObject> { pub fn updatevalues(&self, vals: &Vec<SomeObject>) -> Vec<SomeObject> {
println!("\nUpdating values");
let mut updated: Vec<SomeObject> = Vec::new(); let mut updated: Vec<SomeObject> = Vec::new();
for a in vals { for a in vals {
@@ -64,17 +62,17 @@ pub mod parser {
let updated_parsed = self.add_prefix(parsed); let updated_parsed = self.add_prefix(parsed);
let myobj: SomeObject = SomeObject { let myobj: SomeObject = SomeObject {
value: updated_parsed.clone() value: updated_parsed.clone(),
}; };
updated.push(myobj); updated.push(myobj);
} }
return updated; return updated;
} }
pub fn removedups(&self, vals: &Vec<SomeObject>) -> Vec<SomeObject> { pub fn removedups(&self, vals: &Vec<SomeObject>) -> Vec<SomeObject> {
println!("\nRemoving duplicates");
let mut tmp: HashSet<String> = HashSet::new(); let mut tmp: HashSet<String> = HashSet::new();
let mut mm: Vec<SomeObject> = Vec::new(); let mut mm: Vec<SomeObject> = Vec::new();
mm.clone_from(vals); mm.clone_from(vals);
@@ -83,31 +81,40 @@ pub mod parser {
let mut updated: Vec<SomeObject> = Vec::new(); let mut updated: Vec<SomeObject> = Vec::new();
for t in tmp { for t in tmp {
let so: SomeObject = SomeObject { let so: SomeObject = SomeObject { value: t.clone() };
value: t.clone()
};
updated.push(so); updated.push(so);
} }
return updated return updated;
} }
pub fn print_values(&self, vals: &Vec<SomeObject>) { pub fn print_values(&self, vals: &Vec<SomeObject>, print_total: bool) {
println!("\nPrinting values");
for o in vals { for o in vals {
println!("Value: {}", o.value); println!("Value: {}", o.value);
} }
if print_total {
println!("\nTotal numbers: {:?}", vals.len());
}
} }
pub fn save_file(&self, vals: Vec<SomeObject>) -> std::io::Result<()> { pub fn save_file(&self, vals: Vec<SomeObject>) -> std::io::Result<()> {
println!("\nSaving file");
let filename: String = String::from("numbers.json"); let filename: String = String::from("numbers.json");
let mut all_numbers: Vec<String> = Vec::new();
let json = serde_json::to_string_pretty(&vals).unwrap(); for val in &vals {
all_numbers.push(val.value.clone());
}
let json = serde_json::to_string_pretty(&all_numbers).unwrap();
let mut file = File::create(filename)?; let mut file = File::create(filename)?;
file.write_all(json.as_bytes())?; file.write_all(json.as_bytes())?;
Ok(()) Ok(())
} }
fn read_lines(&self, filename: &str) -> std::io::Result<std::io::Lines<BufReader<File>>> { fn read_lines(&self, filename: &str) -> std::io::Result<std::io::Lines<BufReader<File>>> {
let file = File::open(filename)?; let file = File::open(filename)?;
Ok(BufReader::new(file).lines()) Ok(BufReader::new(file).lines())
@@ -157,11 +164,10 @@ pub mod parser {
} }
} }
return parsed return parsed;
} }
} }
#[cfg(test)] #[cfg(test)]
mod tests { mod tests {
use super::*; use super::*;
@@ -169,7 +175,9 @@ pub mod parser {
#[test] #[test]
fn removing_text() { fn removing_text() {
let sometext: String = String::from("a1234567890"); let sometext: String = String::from("a1234567890");
let numberparser = NumberParser { filepath: String::from("")}; let numberparser = NumberParser {
filepath: String::new(),
};
let removetext = numberparser.remove_some_data(&sometext); let removetext = numberparser.remove_some_data(&sometext);
let mut result = true; let mut result = true;
@@ -188,7 +196,9 @@ pub mod parser {
#[test] #[test]
fn adding_prefix() { fn adding_prefix() {
let sometext: String = String::from("1234567890"); let sometext: String = String::from("1234567890");
let numberparser = NumberParser { filepath: String::from("")}; let numberparser = NumberParser {
filepath: String::new(),
};
let modified = numberparser.add_prefix(sometext); let modified = numberparser.add_prefix(sometext);
let chars = modified.chars().clone(); let chars = modified.chars().clone();
@@ -200,4 +210,3 @@ pub mod parser {
} }
} }
} }