patchwork_csv_utils 0.1.7-x86_64-linux → 0.1.9-x86_64-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c481a9b1277460f51834e1b1b0f7c9dd95a99d0878a03dd4f556532537598262
-  data.tar.gz: 8c124c3f8bd535d3ae10d9b5618f0161349efb49d9c1751410f74bc5e929e569
+  metadata.gz: e62c8af2ccfe8ef8dbdde1f1e38159e9a21938b13f702db03c88b02821498adf
+  data.tar.gz: 521fbb4faaf539e3c9b0bc7f9592ff78337a0681d4ac5172f180030fcaee7dd7
 SHA512:
-  metadata.gz: ceab7828e522af6071cb642a5966908366dc08983dd8ae8d59320a81756747c3ee583f88172245bff05946d4563a162e0e3e26d3560f447bf3ba16881a0e1f8d
-  data.tar.gz: b0ca956f8b46e3267ba80a5b5784c0a61926a69ddb0a414299f538e8d0e46aa68b521cd9ee33ca76e8732d88fab89eb7e92fcdca865a3ae6fa1f471fdb93e8b6
+  metadata.gz: 3f149641716466188ef4e3b7ec51d409dcf33bfb5258ae7787e5ce0594a34306fa051817f88a307b611149390721bff41cfd5732515b8f86e51e96481eed7d41
+  data.tar.gz: feb32457cce07efc5d3e2b0d0b64496049499b5370d33a3aa1ee5f62333f2058c1b5913ee1625e981e50cde7810a5d070258ed8ca9345a0dc8bb800d9ff3ed94

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    patchwork_csv_utils (0.1.7)
+    patchwork_csv_utils (0.1.9)
 
 GEM
   remote: https://rubygems.org/
@@ -67,4 +67,4 @@ DEPENDENCIES
   rubocop (~> 1.21)
 
 BUNDLED WITH
-   2.4.4
+   2.4.10

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"]) {
@@ -19,6 +19,7 @@ pub fn transform_csv(ruby: &Ruby, csv_path: String, target_path: String, exclusi
     let mut wtr = Writer::from_path(target_path).map_err(|e| magnus_err(ruby, e, "target_path"))?;
     let headers = csv.headers().map_err(|e| magnus_err(ruby, e, "csv_path headers"))?;
     let header_map: HashMap<String, usize> = headers.iter().enumerate().map(|(i, h)| (h.to_string(), i)).collect();
+    let inverse_header_map: HashMap<usize, String> = headers.iter().enumerate().map(|(i, h)| (i, h.to_string())).collect();
 
     wtr.write_byte_record(headers.as_byte_record()).map_err(|e| magnus_err(ruby, e, "write_byte_record"))?;
 
@@ -41,13 +42,13 @@ pub fn transform_csv(ruby: &Ruby, csv_path: String, target_path: String, exclusi
         let record = record.iter().enumerate().map(|(i, c)| {
             let c = c.trim_end();
             if i == *date {
-                let current = string_to_datetime(c).ok_or(to_datetime_error(ruby, c, ri, i))?;
+                let current = string_to_datetime(c).ok_or(to_datetime_error(ruby, c, ri, "Date"))?;
                 date_value = current;
                 Ok(current.to_string())
             } else if i == *start || i == *end || i == *actual_start || i == *actual_end {
-                let current_time = string_to_time(c).ok_or(to_datetime_error(ruby, c, ri, i))?;
-                let datetime = transform_time_to_datetime(date_value, current_time);
-                Ok(datetime.to_string())
+                if c.is_empty() { return Ok(c.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())
             }
@@ -62,15 +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()
 }
@@ -79,10 +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: usize) -> 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"]) {
@@ -44,6 +44,9 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>, header_ma
         if skip_excluded_rows(&request_id, r, &exclusions) { continue; }
         if skip_empty_rows(r) { continue; }
         if skip_rows_with_no_request_id(&request_id, r) { continue; }
+        if date_value_is_not_present(&date, r) {
+            return Err(magnus::Error::new(ruby.exception_standard_error(), format!("Date value is not present in row: {}", ri)));
+        }
 
         for (i, c) in r.iter().enumerate() {
             match *c {
@@ -53,7 +56,7 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>, header_ma
                 }
                 Data::Float(ref f) => write!(dest, "{}", f),
                 Data::DateTime(ref d) => {
-                    let mut current = d.as_datetime().unwrap_or_default();
+                    let mut current = d.as_datetime().ok_or(to_datetime_error(ruby, &d.to_string(), ri, "Date"))?;
                     if i == *date {
                         date_value = current;
                     } else if i == *start || i == *end || i == *actual_start || i == *actual_end {
@@ -74,6 +77,10 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>, header_ma
     Ok(())
 }
 
+fn date_value_is_not_present(date: &usize, r: &[Data]) -> bool {
+    r[*date] == Data::Empty
+}
+
 fn skip_excluded_rows(request_id: &usize, r: &[Data], exclusions: &Vec<String>) -> bool {
     let value = r[*request_id].to_string();
     exclusions.contains(&value.to_string())

data/lib/csv_utils/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module CsvUtils
-  VERSION = '0.1.7'
+  VERSION = '0.1.9'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: patchwork_csv_utils
 version: !ruby/object:Gem::Version
-  version: 0.1.7
+  version: 0.1.9
 platform: x86_64-linux
 authors:
 - kingsley.hendrickse
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2024-08-07 00:00:00.000000000 Z
+date: 2024-08-08 00:00:00.000000000 Z
 dependencies: []
 description: Deduplication of CSV files and XLS to CSV conversion.
 email: