patchwork_csv_utils 0.1.8-x86_64-linux → 0.1.10-x86_64-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 557cec4f7b89652d9701343e28ff47c43d379c8dbee9f4614964a91dc7f26cf2
-  data.tar.gz: 62cd2db2316ad54621d110ef397e45aa645a42e7c8ae26eba049ef69d57edb92
+  metadata.gz: 55b3b6982ebaadca79bd6b458a51be253d07c6e58bc7270f9fde70f8b535d349
+  data.tar.gz: ba693a5d934e92637279159d61f47b16cb9ec4594b5afa22fa2cd279ed2983a7
 SHA512:
-  metadata.gz: 5c237bb939e377dfe6448053edac10c54a9eefbaf8216c844fd78ffba3af9a7b493f8ea6afd1b05ce818b623339b41ea80b468c4b3f86b285225381f54d642cb
-  data.tar.gz: 735cf9537f306962790b7066c7f619f6691cff530ad72b7b8d6b3c402c58fe00f2dd43e4c481fdbeb32307812f00fc6df425eeda9b2bcf7ba047580f1f5b5b38
+  metadata.gz: 4a6bb7dbe3b9fcdb7d15335eca40489b5237f71f1145479c6f3aa588f70891a5f8f15e1e73cf3c38fdde59c2df2a5dce84a04404cfeacbb6508474f74b2bebf4
+  data.tar.gz: dd040e99cfebdf8c2672fda983c5d444e70c581fba101b0b35ebcfa46833b46dec12f9765f16833a42bfd248739be717292a485f5bfd719c7a69fd91791d4a9a

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    patchwork_csv_utils (0.1.8)
+    patchwork_csv_utils (0.1.10)
 
 GEM
   remote: https://rubygems.org/

data/ext/csv_utils/src/utils/csv.rs

@@ -3,9 +3,9 @@ use std::fs::File;
 
 use chrono::{NaiveDate, NaiveDateTime, NaiveTime, Utc};
 use csv::{StringRecord, Writer};
-use magnus::{RArray, Ruby};
+use magnus::{Error, RArray, Ruby};
 
-use crate::utils::{FileExtension, magnus_err, missing_header};
+use crate::utils::{FileExtension, magnus_err, missing_header, to_datetime_error};
 
 pub fn transform_csv(ruby: &Ruby, csv_path: String, target_path: String, exclusions: RArray) -> magnus::error::Result<()> {
     if !csv_path.has_extension(&["csv"]) {
@@ -47,11 +47,8 @@ pub fn transform_csv(ruby: &Ruby, csv_path: String, target_path: String, exclusi
                 Ok(current.to_string())
             } else if i == *start || i == *end || i == *actual_start || i == *actual_end {
                 if c.is_empty() { return Ok(c.to_string()); }
-                let unknown = "Unknown".to_string();
-                let column_name = inverse_header_map.get(&i).unwrap_or(&unknown);
-                let current_time = string_to_time(c).ok_or(to_datetime_error(ruby, c, ri, column_name))?;
-                let datetime = transform_time_to_datetime(date_value, current_time);
-                Ok(datetime.to_string())
+                let column_name = get_column_name(&inverse_header_map, &i);
+                process_datetime(ruby, ri, date_value, c, &column_name)
             } else {
                 Ok(c.to_string())
             }
@@ -66,15 +63,39 @@ pub fn transform_csv(ruby: &Ruby, csv_path: String, target_path: String, exclusi
     Ok(())
 }
 
+fn process_datetime(ruby: &Ruby, ri: usize, date_value: NaiveDateTime, c: &str, column_name: &String) -> magnus::error::Result<String> {
+    let maybe_correct = correct_datetime(c);
+    if let Some(correct) = maybe_correct {
+        return Ok(correct.to_string());
+    }
+
+    let current_time = string_to_time(c).ok_or(to_datetime_error(ruby, c, ri, column_name))?;
+    let datetime = transform_time_to_datetime(date_value, current_time);
+    Ok(datetime.to_string())
+}
+
+fn get_column_name(inverse_header_map: &HashMap<usize, String>, i: &usize) -> String {
+    let unknown = "Unknown".to_string();
+    let column_name = inverse_header_map.get(&i).unwrap_or(&unknown);
+    column_name.to_string()
+}
+
 fn skip_excluded_rows(request_id: &usize, r: &StringRecord, exclusions: &Vec<String>) -> bool {
     let value = r.get(*request_id).unwrap_or_default();
     exclusions.contains(&value.to_string())
 }
 
 fn string_to_datetime(s: &str) -> Option<NaiveDateTime> {
+    let maybe_correct = correct_datetime(s);
+    if maybe_correct.is_some() { return maybe_correct; }
+
     NaiveDate::parse_from_str(s, "%d-%b-%y").ok().map(|d| d.and_hms_opt(0, 0, 0)).flatten()
 }
 
+fn correct_datetime(s: &str) -> Option<NaiveDateTime> {
+    NaiveDateTime::parse_from_str(s, "%Y-%m-%d %H:%M:%S").ok()
+}
+
 fn string_to_time(s: &str) -> Option<NaiveTime> {
     NaiveTime::parse_from_str(s, "%H:%M").ok()
 }
@@ -83,10 +104,6 @@ fn transform_time_to_datetime(t1: NaiveDateTime, t2: NaiveTime) -> NaiveDateTime
     NaiveDateTime::new(t1.date(), t2)
 }
 
-fn to_datetime_error(ruby: &Ruby, value: &str, row: usize, col: &str) -> magnus::Error {
-    magnus::Error::new(ruby.exception_standard_error(), format!("Could not parse datetime '{}', row: {}, col: {}", value, row, col))
-}
-
 fn has_empty_first_col_skip_row(record: &StringRecord) -> bool {
     record[0].is_empty()
 }

data/ext/csv_utils/src/utils/mod.rs

@@ -15,6 +15,10 @@ fn magnus_err<E: Error>(ruby: &Ruby, e: E, msg: &str) -> magnus::Error {
     magnus::Error::new(ruby.exception_standard_error(), format!("{}: {}", msg, e.to_string()))
 }
 
+fn to_datetime_error(ruby: &Ruby, value: &str, row: usize, col: &str) -> magnus::Error {
+    magnus::Error::new(ruby.exception_standard_error(), format!("Could not parse datetime '{}', row: {}, col: {}", value, row, col))
+}
+
 pub trait FileExtension {
     fn has_extension<S: AsRef<str>>(&self, extensions: &[S]) -> bool;
 }

data/ext/csv_utils/src/utils/xls.rs

@@ -6,7 +6,7 @@ use calamine::{Data, open_workbook, Range, Reader, Xls};
 use chrono::{NaiveDateTime, Utc};
 use magnus::{RArray, Ruby};
 
-use crate::utils::{FileExtension, magnus_err, missing_header};
+use crate::utils::{FileExtension, magnus_err, missing_header, to_datetime_error};
 
 pub fn to_csv(ruby: &Ruby, xls_path: String, target_path: String, exclusions: RArray) -> magnus::error::Result<()> {
     if !xls_path.has_extension(&["xls"]) {
@@ -98,10 +98,6 @@ fn transform_time_to_datetime(t1: NaiveDateTime, t2: NaiveDateTime) -> NaiveDate
     NaiveDateTime::new(t1.date(), t2.time())
 }
 
-fn to_datetime_error(ruby: &Ruby, value: &str, row: usize, col: &str) -> magnus::Error {
-    magnus::Error::new(ruby.exception_standard_error(), format!("Could not parse datetime '{}', row: {}, col: {}", value, row, col))
-}
-
 fn handle_commas<W: Write>(dest: &mut W, s: &str) -> std::io::Result<()> {
     if s.contains(",") {
         write!(dest, "{:?}", clean_strings(s).trim_end())

data/lib/csv_utils/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module CsvUtils
-  VERSION = '0.1.8'
+  VERSION = '0.1.10'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: patchwork_csv_utils
 version: !ruby/object:Gem::Version
-  version: 0.1.8
+  version: 0.1.10
 platform: x86_64-linux
 authors:
 - kingsley.hendrickse
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2024-08-07 00:00:00.000000000 Z
+date: 2024-08-09 00:00:00.000000000 Z
 dependencies: []
 description: Deduplication of CSV files and XLS to CSV conversion.
 email: