Add practice exercise: ocr-numbers

config.json

@@ -378,6 +378,14 @@
         "prerequisites": [],
         "difficulty": 8
       },
+      {
+        "slug": "ocr-numbers",
+        "name": "OCR Numbers",
+        "uuid": "46c8fd20-887f-4cd6-ac3a-9717d169de1d",
+        "practices": [],
+        "prerequisites": [],
+        "difficulty": 8
+      },
       {
         "slug": "pascals-triangle",
         "name": "Pascal's Triangle",
@@ -441,19 +449,19 @@
         "practices": [],
         "prerequisites": [],
         "difficulty": 8
-      },        
+      },
       {
-        "slug": "saddle-points",
-        "name": "Saddle Points",
-        "uuid": "d050e56b-9f86-416c-baa3-10a98f47b944",  
+        "slug": "run-length-encoding",
+        "name": "Run-Length Encoding",
+        "uuid": "065feae7-f6fc-46b9-a226-d3d9df9d192b",
         "practices": [],
         "prerequisites": [],
         "difficulty": 8
       },
       {
-        "slug": "run-length-encoding",
-        "name": "Run-Length Encoding",
-        "uuid": "065feae7-f6fc-46b9-a226-d3d9df9d192b",
+        "slug": "saddle-points",
+        "name": "Saddle Points",
+        "uuid": "d050e56b-9f86-416c-baa3-10a98f47b944",
         "practices": [],
         "prerequisites": [],
         "difficulty": 8

exercises/practice/ocr-numbers/.docs/instructions.md

@@ -0,0 +1,79 @@
+# Instructions
+
+Given a 3 x 4 grid of pipes, underscores, and spaces, determine which number is represented, or whether it is garbled.
+
+## Step One
+
+To begin with, convert a simple binary font to a string containing 0 or 1.
+
+The binary font uses pipes and underscores, four rows high and three columns wide.
+
+```text
+     _   #
+    | |  # zero.
+    |_|  #
+         # the fourth row is always blank
+```
+
+Is converted to "0"
+
+```text
+         #
+      |  # one.
+      |  #
+         # (blank fourth row)
+```
+
+Is converted to "1"
+
+If the input is the correct size, but not recognizable, your program should return '?'
+
+If the input is the incorrect size, your program should return an error.
+
+## Step Two
+
+Update your program to recognize multi-character binary strings, replacing garbled numbers with ?
+
+## Step Three
+
+Update your program to recognize all numbers 0 through 9, both individually and as part of a larger string.
+
+```text
+ _
+ _|
+|_
+
+```
+
+Is converted to "2"
+
+```text
+      _  _     _  _  _  _  _  _  #
+    | _| _||_||_ |_   ||_||_|| | # decimal numbers.
+    ||_  _|  | _||_|  ||_| _||_| #
+                                 # fourth line is always blank
+```
+
+Is converted to "1234567890"
+
+## Step Four
+
+Update your program to handle multiple numbers, one per line.
+When converting several lines, join the lines with commas.
+
+```text
+    _  _
+  | _| _|
+  ||_  _|
+
+    _  _
+|_||_ |_
+  | _||_|
+
+ _  _  _
+  ||_||_|
+  ||_| _|
+
+```
+
+Is converted to "123,456,789".

exercises/practice/ocr-numbers/.meta/config.json

@@ -0,0 +1,19 @@
+{
+  "authors": [
+    "jimmytty"
+  ],
+  "files": {
+    "solution": [
+      "ocr-numbers.sql"
+    ],
+    "test": [
+      "ocr-numbers_test.sql"
+    ],
+    "example": [
+      ".meta/example.sql"
+    ]
+  },
+  "blurb": "Given a 3 x 4 grid of pipes, underscores, and spaces, determine which number is represented, or whether it is garbled.",
+  "source": "Inspired by the Bank OCR kata",
+  "source_url": "https://codingdojo.org/kata/BankOCR/"
+}

exercises/practice/ocr-numbers/.meta/example.sql

@@ -0,0 +1,130 @@
+UPDATE "ocr-numbers"
+   SET error = 'Number of input lines is not a multiple of four'
+ WHERE (LENGTH(input) - LENGTH(REPLACE(input, CHAR(10), '')) + 1) % 4 != 0
+;
+UPDATE "ocr-numbers"
+   SET error = 'Number of input columns is not a multiple of three'
+ WHERE LENGTH(REPLACE(input, CHAR(10), '')) % 3 != 0
+;
+
+
+DROP TABLE IF EXISTS dict;
+CREATE TEMPORARY TABLE dict AS
+WITH RECURSIVE rcte (string, idx, font, digit) AS (
+  VALUES (
+    (WITH cte (fonts) AS (
+      VALUES
+      ('    _  _     _  _  _  _  _  _ '),
+      ('  | _| _||_||_ |_   ||_||_|| |'),
+      ('  ||_  _|  | _||_|  ||_| _||_|'),
+      ('                              '))
+    SELECT GROUP_CONCAT(fonts, CHAR(10)) FROM cte),
+    1, NULL, 0
+  )
+  UNION ALL
+  SELECT string,
+         idx + 3,
+         REPLACE(
+           PRINTF('%s\n%s\n%s\n%s',
+             SUBSTR(string, INSTR(string, CHAR(10)) * 0 + idx, 3),
+             SUBSTR(string, INSTR(string, CHAR(10)) * 1 + idx, 3),
+             SUBSTR(string, INSTR(string, CHAR(10)) * 2 + idx, 3),
+             SUBSTR(string, INSTR(string, CHAR(10)) * 3 + idx, 3)
+           ),
+           '\n',
+           CHAR(10)
+         ),
+         IIF(digit + 1 = 10, 0, digit + 1)
+    FROM rcte
+   WHERE idx < 30
+) SELECT font, digit FROM rcte WHERE font NOTNULL;
+
+UPDATE "ocr-numbers"
+   SET result = (
+         WITH
+           split_lines AS (
+             WITH RECURSIVE rcte (string, idx, line) AS (
+               VALUES (input, 0, NULL)
+               UNION ALL
+               SELECT string,
+                      idx + 4,
+                      LTRIM(
+                        PRINTF(
+                          '%s%s%s%s',
+                          SUBSTR(
+                            string,
+                            INSTR(string, char(10)) * (idx + 0),
+                            INSTR(string, char(10))
+                          ),
+                          SUBSTR(
+                            string,
+                            INSTR(string, char(10)) * (idx + 1),
+                            INSTR(string, char(10))
+                          ),
+                          SUBSTR(
+                            string,
+                            INSTR(string, char(10)) * (idx + 2),
+                            INSTR(string, char(10))
+                          ),
+                          SUBSTR(
+                            string,
+                            INSTR(string, char(10)) * (idx+3),
+                            INSTR(string, char(10))
+                          )
+                        ),
+                        CHAR(10)
+                      )
+                 FROM rcte
+                 WHERE idx <=
+                       LENGTH(string) - LENGTH(replace(string, char(10),''))
+            ) SELECT line FROM rcte WHERE line NOTNULL
+          ),
+          converter AS (
+            SELECT line,
+                   (WITH RECURSIVE split_numbers (string, idx, font) AS (
+                     VALUES (line, 1, NULL)
+                     UNION ALL
+                     SELECT string,
+                            idx + 3,
+                            REPLACE(
+                              PRINTF(
+                                '%s\n%s\n%s\n%s',
+                                SUBSTR(
+                                  string,
+                                  INSTR(string, CHAR(10)) * 0 + idx, 3
+                                ),
+                                SUBSTR(
+                                  string,
+                                  INSTR(string, CHAR(10)) * 1 + idx, 3
+                                ),
+                                SUBSTR(
+                                  string,
+                                  INSTR(string, CHAR(10)) * 2 + idx, 3
+                                ),
+                                SUBSTR(
+                                  string,
+                                  INSTR(string, CHAR(10)) * 3 + idx, 3
+                                )
+                              ),
+                              '\n',
+                              CHAR(10)
+                            )
+               FROM split_numbers
+               WHERE idx < (SELECT INSTR(string, CHAR(10)))
+           )
+           SELECT GROUP_CONCAT(digit, '') AS number
+             FROM (
+               SELECT COALESCE(
+                        (SELECT digit
+                           FROM dict
+                          WHERE dict.font = split_numbers.font),
+                          '?'
+                      ) AS digit
+                 FROM split_numbers WHERE font NOTNULL
+             )
+                   ) AS number
+              FROM split_lines
+          ) SELECT GROUP_CONCAT(number) AS number FROM converter
+   )
+ WHERE error ISNULL
+;

exercises/practice/ocr-numbers/.meta/tests.toml

@@ -0,0 +1,61 @@
+# This is an auto-generated file.
+#
+# Regenerating this file via `configlet sync` will:
+# - Recreate every `description` key/value pair
+# - Recreate every `reimplements` key/value pair, where they exist in problem-specifications
+# - Remove any `include = true` key/value pair (an omitted `include` key implies inclusion)
+# - Preserve any other key/value pair
+#
+# As user-added comments (using the # character) will be removed when this file
+# is regenerated, comments can be added via a `comment` key.
+
+[5ee54e1a-b554-4bf3-a056-9a7976c3f7e8]
+description = "Recognizes 0"
+
+[027ada25-17fd-4d78-aee6-35a19623639d]
+description = "Recognizes 1"
+
+[3cce2dbd-01d9-4f94-8fae-419a822e89bb]
+description = "Unreadable but correctly sized inputs return ?"
+
+[cb19b733-4e36-4cf9-a4a1-6e6aac808b9a]
+description = "Input with a number of lines that is not a multiple of four raises an error"
+
+[235f7bd1-991b-4587-98d4-84206eec4cc6]
+description = "Input with a number of columns that is not a multiple of three raises an error"
+
+[4a841794-73c9-4da9-a779-1f9837faff66]
+description = "Recognizes 110101100"
+
+[70c338f9-85b1-4296-a3a8-122901cdfde8]
+description = "Garbled numbers in a string are replaced with ?"
+
+[ea494ff4-3610-44d7-ab7e-72fdef0e0802]
+description = "Recognizes 2"
+
+[1acd2c00-412b-4268-93c2-bd7ff8e05a2c]
+description = "Recognizes 3"
+
+[eaec6a15-be17-4b6d-b895-596fae5d1329]
+description = "Recognizes 4"
+
+[440f397a-f046-4243-a6ca-81ab5406c56e]
+description = "Recognizes 5"
+
+[f4c9cf6a-f1e2-4878-bfc3-9b85b657caa0]
+description = "Recognizes 6"
+
+[e24ebf80-c611-41bb-a25a-ac2c0f232df5]
+description = "Recognizes 7"
+
+[b79cad4f-e264-4818-9d9e-77766792e233]
+description = "Recognizes 8"
+
+[5efc9cfc-9227-4688-b77d-845049299e66]
+description = "Recognizes 9"
+
+[f60cb04a-42be-494e-a535-3451c8e097a4]
+description = "Recognizes string of decimal numbers"
+
+[b73ecf8b-4423-4b36-860d-3710bdb8a491]
+description = "Numbers separated by empty lines are recognized. Lines are joined by commas."

exercises/practice/ocr-numbers/create_fixture.sql

@@ -0,0 +1,12 @@
+DROP TABLE IF EXISTS "ocr-numbers";
+CREATE TABLE "ocr-numbers" (
+    input   TEXT NOT NULL,
+    result  TEXT         ,
+    error   TEXT
+);
+
+.mode csv
+.import ./data.csv "ocr-numbers"
+
+UPDATE "ocr-numbers" SET result = NULL, error = NULL;
+UPDATE "ocr-numbers" SET input = REPLACE(input, '\n', CHAR(10));

exercises/practice/ocr-numbers/create_test_table.sql

@@ -0,0 +1,38 @@
+DROP TABLE IF EXISTS tests;
+CREATE TABLE IF NOT EXISTS tests (
+    -- uuid and description are taken from the test.toml file
+    uuid TEXT PRIMARY KEY,
+    description TEXT NOT NULL,
+    -- The following section is needed by the online test-runner
+    status TEXT DEFAULT 'fail',
+    message TEXT,
+    output TEXT,
+    test_code TEXT,
+    task_id INTEGER DEFAULT NULL,
+    -- Here are columns for the actual tests
+    input TEXT NOT NULL,
+    expected_result TEXT,
+    expected_error TEXT
+);
+
+INSERT INTO tests (uuid, description, input, expected_result, expected_error)
+VALUES
+('5ee54e1a-b554-4bf3-a056-9a7976c3f7e8', 'Recognizes 0', ' _ \n| |\n|_|\n   ', '0', NULL),
+('027ada25-17fd-4d78-aee6-35a19623639d', 'Recognizes 1', '   \n  |\n  |\n   ', '1', NULL),
+('3cce2dbd-01d9-4f94-8fae-419a822e89bb', 'Unreadable but correctly sized inputs return ?', '   \n  _\n  |\n   ', '?', NULL),
+('cb19b733-4e36-4cf9-a4a1-6e6aac808b9a', 'Input with a number of lines that is not a multiple of four raises an error', ' _ \n| |\n   ', NULL, 'Number of input lines is not a multiple of four'),
+('235f7bd1-991b-4587-98d4-84206eec4cc6', 'Input with a number of columns that is not a multiple of three raises an error', '    \n   |\n   |\n    ', NULL, 'Number of input columns is not a multiple of three'),
+('4a841794-73c9-4da9-a779-1f9837faff66', 'Recognizes 110101100', '       _     _        _  _ \n  |  || |  || |  |  || || |\n  |  ||_|  ||_|  |  ||_||_|\n                           ', '110101100', NULL),
+('70c338f9-85b1-4296-a3a8-122901cdfde8', 'Garbled numbers in a string are replaced with ?', '       _     _           _ \n  |  || |  || |     || || |\n  |  | _|  ||_|  |  ||_||_|\n                           ', '11?10?1?0', NULL),
+('ea494ff4-3610-44d7-ab7e-72fdef0e0802', 'Recognizes 2', ' _ \n _|\n|_ \n   ', '2', NULL),
+('1acd2c00-412b-4268-93c2-bd7ff8e05a2c', 'Recognizes 3', ' _ \n _|\n _|\n   ', '3', NULL),
+('eaec6a15-be17-4b6d-b895-596fae5d1329', 'Recognizes 4', '   \n|_|\n  |\n   ', '4', NULL),
+('440f397a-f046-4243-a6ca-81ab5406c56e', 'Recognizes 5', ' _ \n|_ \n _|\n   ', '5', NULL),
+('f4c9cf6a-f1e2-4878-bfc3-9b85b657caa0', 'Recognizes 6', ' _ \n|_ \n|_|\n   ', '6', NULL),
+('e24ebf80-c611-41bb-a25a-ac2c0f232df5', 'Recognizes 7', ' _ \n  |\n  |\n   ', '7', NULL),
+('b79cad4f-e264-4818-9d9e-77766792e233', 'Recognizes 8', ' _ \n|_|\n|_|\n   ', '8', NULL),
+('5efc9cfc-9227-4688-b77d-845049299e66', 'Recognizes 9', ' _ \n|_|\n _|\n   ', '9', NULL),
+('f60cb04a-42be-494e-a535-3451c8e097a4', 'Recognizes string of decimal numbers', '    _  _     _  _  _  _  _  _ \n  | _| _||_||_ |_   ||_||_|| |\n  ||_  _|  | _||_|  ||_| _||_|\n                              ', '1234567890', NULL),
+('b73ecf8b-4423-4b36-860d-3710bdb8a491', 'Numbers separated by empty lines are recognized. Lines are joined by commas.', '    _  _ \n  | _| _|\n  ||_  _|\n         \n    _  _ \n|_||_ |_ \n  | _||_|\n         \n _  _  _ \n  ||_||_|\n  ||_| _|\n         ', '123,456,789', NULL);
+
+UPDATE tests SET input = REPLACE(input, '\n', CHAR(10));