compare: locate additional columns to the left of diff columns; add t…

…est (#146)
liquidaty · Dec 31, 2023 · 7b64541 · 7b64541
1 parent 8541f33
commit 7b64541
Show file tree

Hide file tree

Showing 6 changed files with 73 additions and 30 deletions.
diff --git a/app/compare.c b/app/compare.c
@@ -155,6 +155,17 @@ static void zsv_compare_output_tuple(struct zsv_compare_data *data,
     }
   }
 
+  // output additional columns
+  for(struct zsv_compare_added_column *ac = data->added_columns; ac; ac = ac->next) {
+    if(!ac->input) {
+      if(data->writer.type != ZSV_COMPARE_OUTPUT_TYPE_JSON)
+        zsv_compare_output_str(data, NULL, ZSV_WRITER_SAME_ROW, 0);
+    } else {
+      struct zsv_cell c = data->get_cell(ac->input, ac->col_ix);
+      zsv_compare_output_strn(data, c.str, c.len, ZSV_WRITER_SAME_ROW, c.quoted);
+    }
+  }
+
   // output column name of this cell
   zsv_compare_output_str(data, colname, ZSV_WRITER_SAME_ROW, 1);
 
@@ -168,17 +179,6 @@ static void zsv_compare_output_tuple(struct zsv_compare_data *data,
     }
   }
 
-  // output additional columns
-  for(struct zsv_compare_added_column *ac = data->added_columns; ac; ac = ac->next) {
-    if(!ac->input) {
-      if(data->writer.type != ZSV_COMPARE_OUTPUT_TYPE_JSON)
-        zsv_compare_output_str(data, NULL, ZSV_WRITER_SAME_ROW, 0);
-    } else {
-      struct zsv_cell c = data->get_cell(ac->input, ac->col_ix);
-      zsv_compare_output_strn(data, c.str, c.len, ZSV_WRITER_SAME_ROW, c.quoted);
-    }
-  }
-
   if(data->writer.type == ZSV_COMPARE_OUTPUT_TYPE_JSON)
     zsv_compare_json_row_end(data);
 }
@@ -359,6 +359,10 @@ static void zsv_compare_output_begin(struct zsv_compare_data *data) {
                                1);
     }
 
+    // write additional column names
+    for(struct zsv_compare_added_column *ac = data->added_columns; ac; ac = ac->next)
+      zsv_compare_header_str(data, ac->colname->name, ZSV_WRITER_SAME_ROW, 1);
+
     // write "Column"
     zsv_compare_header_str(data, (const unsigned char *)"Column", ZSV_WRITER_SAME_ROW, 0);
 
@@ -368,10 +372,6 @@ static void zsv_compare_output_begin(struct zsv_compare_data *data) {
       zsv_compare_header_str(data, (const unsigned char *)input->path, ZSV_WRITER_SAME_ROW, 1);
     }
 
-    // write additional column names
-    for(struct zsv_compare_added_column *ac = data->added_columns; ac; ac = ac->next)
-      zsv_compare_header_str(data, ac->colname->name, ZSV_WRITER_SAME_ROW, 1);
-
     if(data->writer.type == ZSV_COMPARE_OUTPUT_TYPE_JSON && !data->writer.object)
       jsonwriter_end_array(data->writer.handle.jsw);
   }
@@ -600,19 +600,19 @@ static int compare_usage() {
   static const char *usage[] = {
     "Usage: compare [options] [file1.csv] [file2.csv] [...]",
     "Options:",
-    "  -h,--help        : show usage",
-    "  -k,--key <field> : specify a field to match rows on",
-    "                     can be specified multiple times",
-    "  -a,--add <field> : specify an additional field to output",
-    "                     will use the [first input] source",
-    "  --sort           : sort on keys before comparing",
-    "  --sort-in-memory : for sorting,  use in-memory instead of temporary db",
-    "                     (see https://www.sqlite.org/inmemorydb.html)",
-    "  --json           : output as JSON",
-    "  --json-compact   : output as compact JSON",
-    "  --json-object    : output as an array of objects",
-    "  --print-key-colname : when outputting key column diffs,",
-    "                        print column name instead of <key>",
+    "  -h,--help          : show usage",
+    "  -k,--key <colname> : specify a column to match rows on",
+    "                       can be specified multiple times",
+    "  -a,--add <colname> : specify an additional column to output",
+    "                       will use the [first input] source",
+    "  --sort             : sort on keys before comparing",
+    "  --sort-in-memory   : for sorting,  use in-memory instead of temporary db",
+    "                       (see https://www.sqlite.org/inmemorydb.html)",
+    "  --json             : output as JSON",
+    "  --json-compact     : output as compact JSON",
+    "  --json-object      : output as an array of objects",
+    "  --print-key-colname: when outputting key column diffs,",
+    "                       print column name instead of <key>",
     "",
     "NOTES",
     "",

diff --git a/app/test/Makefile b/app/test/Makefile
@@ -494,3 +494,9 @@ test-compare: test-%: ${BUILD_DIR}/bin/zsv_%${EXE}
 
 	@(${PREFIX} $< compare/t1.csv compare/t7.csv compare/t3.csv --print-key-colname -k c ${REDIRECT1} ${TMP_DIR}/[email protected] && \
 	${CMP} ${TMP_DIR}/[email protected] expected/[email protected] && ${TEST_PASS} || ${TEST_FAIL})
+
+	@(${PREFIX} $< compare/t1.csv compare/t7.csv compare/t3.csv --print-key-colname -k c ${REDIRECT1} ${TMP_DIR}/[email protected] && \
+	${CMP} ${TMP_DIR}/[email protected] expected/[email protected] && ${TEST_PASS} || ${TEST_FAIL})
+
+	@(${PREFIX} $< ../../data/compare/t1.csv ../../data/compare/t2.csv --add AccentCity --sort -k country -k city ${REDIRECT1} ${TMP_DIR}/[email protected] && \
+	${CMP} ${TMP_DIR}/[email protected] expected/[email protected] && ${TEST_PASS} || ${TEST_FAIL})
diff --git a/app/test/expected/test-compare.out10 b/app/test/expected/test-compare.out10
@@ -0,0 +1,9 @@
+country,city,AccentCity,Column,../../data/compare/t1.csv,../../data/compare/t2.csv
+cn,fulongling,Placken,<key>,Missing,
+de,placken,Placken,Longitude,8.433333,10.4
+ie,burtown cross roads,Oggal,<key>,Missing,
+kr,chusamdong,Cvetovo,<key>,Missing,
+pl,ciesle male,Ciesle Male,AccentCity,Ciesle Male,Ciesle XXX
+ru,chishmabash,Chishmabash,<key>,,Missing
+tr,yenioe,Lituhi Mission,<key>,Missing,
+zr,kakova,Kakova,Region,9,XX
diff --git a/data/compare/t1.csv b/data/compare/t1.csv
@@ -0,0 +1,12 @@
+Country,City,AccentCity,Region,Population,Latitude,Longitude
+de,placken,Placken,7,,52.15,8.433333
+gb,duffryn,Duffryn,Z3,,51.4375,-3.304444
+id,kemitang,Kemitang,7,,-7.544444,109.183333
+ie,oggal,Oggal,2,,54.2597222,-7.9266667
+mk,cvetovo,Cvetovo,92,,41.8580556,21.4097222
+pl,ciesle male,Ciesle Male,86,,52.176861,17.649143
+ru,chishmabash,Chishmabash,73,,55.4708,53.8996
+tz,lituhi mission,Lituhi Mission,14,,-10.55,34.6
+us,steep falls,Steep Falls,ME,,43.7938889,-70.6530556
+za,hota,Hota,5,,-31.640685,27.681357
+zr,kakova,Kakova,9,,0.7333333,29.0166667
diff --git a/data/compare/t2.csv b/data/compare/t2.csv
@@ -0,0 +1,15 @@
+Region,Population,Latitude,Longitude,Country,City,AccentCity
+92,,41.8580556,21.4097222,mk,cvetovo,Cvetovo
+86,,52.176861,17.649143,pl,ciesle male,Ciesle XXX
+39,,41.677473,27.067859,tr,yenioe,Yenioe
+14,,-10.55,34.6,tz,lituhi mission,Lituhi Mission
+ME,,43.7938889,-70.6530556,us,steep falls,Steep Falls
+5,,-31.640685,27.681357,za,hota,Hota
+XX,,0.7333333,29.0166667,zr,kakova,Kakova
+3,,26.934908,115.628584,cn,fulongling,Fulongling
+7,,52.15,10.4,de,placken,Placken
+Z3,,51.4375,-3.304444,gb,duffryn,Duffryn
+7,,-7.544444,109.183333,id,kemitang,Kemitang
+12,,52.9911111,-6.8938889,ie,burtown cross roads,Burtown XXX
+2,,54.2597222,-7.9266667,ie,oggal,Oggal
+16,,34.788889,127.670833,kr,chusamdong,Chusamdong
diff --git a/docs/compare.md b/docs/compare.md
@@ -60,7 +60,8 @@ Row matching and sorting is handled as follows:
 
 Imagine we want to compare the following two tables:
 
-### Table 1 (t1.csv)
+### Table 1 [t1.csv](../data/compare/t1.csv)
+
 
 |Country|City|AccentCity|Region|Population|Latitude|Longitude|
 |--|--|--|--|--|--|--|
@@ -76,7 +77,7 @@ Imagine we want to compare the following two tables:
 |za|hota|Hota|05||-31.640685|27.681357|
 |zr|kakova|Kakova|09||0.7333333|29.0166667|
 
-### Table 2 (t2.csv)
+### Table 2 [t2.csv](../data/compare/t2.csv)
 
 |Region|Population|Latitude|Longitude|Country|City|AccentCity|
 |--|--|--|--|--|--|--|