Merge 3e0c47b into dc6a598

MobilityData · May 5, 2023 · 68964e2 · 68964e2
2 parents dc6a598 + 3e0c47b
commit 68964e2
Show file tree

Hide file tree

Showing 87 changed files with 366 additions and 373 deletions.
diff --git a/RULES.md b/RULES.md
@@ -64,7 +64,7 @@ Each Notice is associated with a severity: `INFO`, `WARNING`, `ERROR`.
 | [`missing_required_column`](#missing_required_column)                                                                             | A required column is missing in the input file.                                                                                                        |
 | [`missing_required_field`](#missing_required_field)                                                                               | A required field is missing.                                                                                                                           |
 | [`missing_required_file`](#missing_required_file)                                                                                 | A required file is missing.                                                                                                                            |
-| [`missing_stop_name`](#missing_stop_name)                                                                                         | `stops.stop_name` is required for `location_type` equal to `0`, `1`, or `2`.                                                                          |
+| [`missing_stop_name`](#missing_stop_name)                                                                                         | `stops.stop_name` is required for `location_type` equal to `0`, `1`, or `2`.                                                                           |
 | [`missing_trip_edge`](#missing_trip_edge)                                                                                         | Missing trip edge `arrival_time` or `departure_time`.                                                                                                  |
 | [`new_line_in_value`](#new_line_in_value)                                                                                         | New line or carriage return in a value in CSV file.                                                                                                    |
 | [`number_out_of_range`](#number_out_of_range)                                                                                     | Out of range value.                                                                                                                                    |
@@ -81,7 +81,7 @@ Each Notice is associated with a severity: `INFO`, `WARNING`, `ERROR`.
 | [`stop_time_timepoint_without_times`](#stop_time_timepoint_without_times)                                                         | `arrival_time` or `departure_time` not specified for timepoint.                                                                                        |
 | [`stop_time_with_arrival_before_previous_departure_time`](#stop_time_with_arrival_before_previous_departure_time)                 | Backwards time travel between stops in `stop_times.txt`                                                                                                |
 | [`stop_time_with_only_arrival_or_departure_time`](#stop_time_with_only_arrival_or_departure_time)                                 | Missing `stop_times.arrival_time` or `stop_times.departure_time`.                                                                                      |
-| [`stop_without_location`](#stop_without_location) | `stop_lat` and/or `stop_lon` is missing for stop with `location_type` equal to`0`, `1`, or `2`
+| [`stop_without_location`](#stop_without_location)                                                                                 | `stop_lat` and/or `stop_lon` is missing for stop with `location_type` equal to`0`, `1`, or `2`                                                         |
 | [`stop_without_zone_id`](#stop_without_zone_id)                                                                                   | Stop without value for `stops.zone_id`.                                                                                                                |
 | [`too_many_rows`](#too_many_rows)                                                                                                 | A CSV file has too many rows.                                                                                                                          |
 | [`transfer_with_invalid_stop_location_type`](#transfer_with_invalid_stop_location_type)                                           | A stop id field from GTFS file `transfers.txt` references a stop that has a `location_type` other than 0 or 1 (aka Stop/Platform or Station).          |
@@ -101,7 +101,7 @@ Each Notice is associated with a severity: `INFO`, `WARNING`, `ERROR`.
 | [`duplicate_route_name`](#duplicate_route_name)                                               | Two distinct routes have either the same `route_short_name`, the same `route_long_name`, or the same combination of `route_short_name` and `route_long_name`. |
 | [`empty_row`](#empty_row)                                                                     | A row in the input file has only spaces.                                                                                                                      |
 | [`equal_shape_distance_same_coordinates`](#equal_shape_distance_same_coordinates)             | Two consecutive points have equal `shape_dist_traveled` and the same lat/lon coordinates in `shapes.txt`.                                                     |
-| [`expired_calendar`](#expired_calendar)                                         | Dataset should not contain date ranges for services that have already expired.
+| [`expired_calendar`](#expired_calendar)                                                       | Dataset should not contain date ranges for services that have already expired.                                                                                |
 | [`fast_travel_between_consecutive_stops`](#fast_travel_between_consecutive_stops)             | A transit vehicle moves too fast between two consecutive stops.                                                                                               |
 | [`fast_travel_between_far_stops`](#fast_travel_between_far_stops)                             | A transit vehicle moves too fast between two far stops.                                                                                                       |
 | [`feed_expiration_date7_days`](#feed_expiration_date7_days)                                   | Dataset should be valid for at least the next 7 days.                                                                                                         |
@@ -114,7 +114,7 @@ Each Notice is associated with a severity: `INFO`, `WARNING`, `ERROR`.
 | [`missing_recommended_field`](#missing_recommended_field)                                     | A recommended field is missing.                                                                                                                               |
 | [`missing_timepoint_column`](#missing_timepoint_column)                                       | `timepoint` column is missing for a dataset.                                                                                                                  |
 | [`missing_timepoint_value`](#missing_timepoint_value)                                         | `stop_times.timepoint` value is missing for a record.                                                                                                         |
-| [`mixed_case_recommended_field`](#mixed_case_recommended_field)                                                       | This field has customer-facing text and should use Mixed Case (should contain upper and lower case letters).                                                                                                         |
+| [`mixed_case_recommended_field`](#mixed_case_recommended_field)                               | This field has customer-facing text and should use Mixed Case (should contain upper and lower case letters).                                                  |
 | [`more_than_one_entity`](#more_than_one_entity)                                               | More than one row in CSV.                                                                                                                                     |
 | [`non_ascii_or_non_printable_char`](#non_ascii_or_non_printable_char)                         | Non ascii or non printable char in  `id`.                                                                                                                     |
 | [`pathway_dangling_generic_node`](#pathway_dangling_generic_node)                             | A generic node has only one incident location in a pathway graph.                                                                                             |

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/CsvParsingFailedNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/CsvParsingFailedNotice.java
@@ -25,8 +25,6 @@
  * Parsing of a CSV file failed.
  *
  * <p>One common case of the problem is when a cell value contains more than 4096 characters.
- *
- * <p>Severity: {@code SeverityLevel.ERROR}
  */
 @GtfsValidationNotice(severity = ERROR)
 public class CsvParsingFailedNotice extends ValidationNotice {

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/DuplicateKeyNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/DuplicateKeyNotice.java
@@ -24,9 +24,9 @@
 import org.mobilitydata.gtfsvalidator.annotation.GtfsValidationNotice.UrlRef;
 
 /**
- * The values of the given key and rows are duplicates.
+ * Duplicated entity.
  *
- * <p>Severity: {@code SeverityLevel.ERROR}
+ * <p>The values of the given key and rows are duplicates.
  */
 @GtfsValidationNotice(
     severity = ERROR,

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/DuplicatedColumnNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/DuplicatedColumnNotice.java
@@ -23,9 +23,9 @@
 import org.mobilitydata.gtfsvalidator.annotation.GtfsValidationNotice.UrlRef;
 
 /**
- * The input file CSV header has the same column name repeated.
+ * Duplicated column in CSV.
  *
- * <p>Severity: {@code SeverityLevel.ERROR}
+ * <p>The input file CSV header has the same column name repeated.
  */
 @GtfsValidationNotice(
     severity = ERROR,

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/EmptyColumnNameNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/EmptyColumnNameNotice.java
@@ -22,9 +22,9 @@
 import org.mobilitydata.gtfsvalidator.annotation.GtfsValidationNotice.SectionRefs;
 
 /**
- * A column name is empty. Such columns are skipped by the validator.
+ * A column name is empty.
  *
- * <p>Severity: {@code SeverityLevel.ERROR}
+ * <p>Such columns are skipped by the validator.
  */
 @GtfsValidationNotice(severity = ERROR, sections = @SectionRefs(FILE_REQUIREMENTS))
 public class EmptyColumnNameNotice extends ValidationNotice {

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/EmptyFileNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/EmptyFileNotice.java
@@ -24,7 +24,9 @@
 /**
  * A CSV file is empty.
  *
- * <p>Severity: {@code SeverityLevel.ERROR}
+ * <p>Empty csv file found in the archive: file does not have any headers, or is a required file and
+ * does not have any data. The GTFS specification requires the first line of each file to contain
+ * field names and required files must have data.
  */
 @GtfsValidationNotice(severity = ERROR, sections = @SectionRefs(FILE_REQUIREMENTS))
 public class EmptyFileNotice extends ValidationNotice {

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/EmptyRowNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/EmptyRowNotice.java
@@ -26,8 +26,6 @@
  *
  * <p>Some CSV parsers, such as Univocity, may misinterpret it as a non-empty row that has a single
  * column which is empty, hence we show a warning.
- *
- * <p>Severity: {@code SeverityLevel.WARNING}
  */
 @GtfsValidationNotice(severity = WARNING, sections = @SectionRefs(FILE_REQUIREMENTS))
 public class EmptyRowNotice extends ValidationNotice {

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/ForeignKeyViolationNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/ForeignKeyViolationNotice.java
@@ -23,13 +23,12 @@
 import org.mobilitydata.gtfsvalidator.annotation.GtfsValidationNotice.UrlRef;
 
 /**
- * The values of the given key and rows of one table cannot be found a values of the given key in
- * another table.
+ * Wrong foreign key.
  *
- * <p>This is the case when a foreign key of one table references a non-existing value in its
- * original table.
- *
- * <p>Severity: {@code SeverityLevel.ERROR}
+ * <p>A foreign key references the primary key of another file. A foreign key violation means that
+ * the foreign key referenced from a given row (the child file) cannot be found in the corresponding
+ * file (the parent file). The Foreign keys are defined in the specification under "Type" for each
+ * file.
  */
 @GtfsValidationNotice(
     severity = ERROR,

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/IOError.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/IOError.java
@@ -21,11 +21,7 @@
 import java.io.IOException;
 import org.mobilitydata.gtfsvalidator.annotation.GtfsValidationNotice;
 
-/**
- * This is related to Input and Output operations in the code.
- *
- * <p>Severity: {@code SeverityLevel.ERROR}
- */
+/** Error in IO operation. */
 @GtfsValidationNotice(severity = ERROR)
 public class IOError extends SystemError {
 

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidColorNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidColorNotice.java
@@ -26,10 +26,7 @@
  *
  * <p>A color must be encoded as a six-digit hexadecimal number. The leading "#" is not included.
  *
- * <p>Example: {@code FFFFFF} for white, {@code 000000} for black or {@code 0039A6} for the A,C,E
- * lines in NYMTA.
- *
- * <p>Severity: {@code SeverityLevel.ERROR}
+ * <p>Example: `FFFFFF` for white, `000000` for black or `0039A6` for the A,C,E lines in NYC MTA.
  */
 @GtfsValidationNotice(severity = ERROR, sections = @SectionRefs(FILED_TYPES))
 public class InvalidColorNotice extends ValidationNotice {

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidCurrencyAmountNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidCurrencyAmountNotice.java
@@ -8,10 +8,12 @@
 import org.mobilitydata.gtfsvalidator.annotation.GtfsValidationNotice.SectionRefs;
 
 /**
- * A currency amount field has a value that does not match the format (e.g. expected number of
- * decimal places) of its corresponding currency code field.
+ * A currency amount field has a value that does not match the format of its corresponding currency
+ * code field.
  *
- * <p>Severity: {@code SeverityLevel.ERROR}
+ * <p>Typically, this means the amount did not have the expected number of decimal places. The
+ * number of decimal places is specified by <a
+ * href="https://en.wikipedia.org/wiki/ISO_4217#Active_codes">ISO 4217</a>.
  *
  * @see org.mobilitydata.gtfsvalidator.annotation.CurrencyAmount
  */

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidCurrencyNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidCurrencyNotice.java
@@ -25,12 +25,9 @@
  * A field contains a wrong currency code.
  *
  * <p>Currency code must follow <a href="https://en.wikipedia.org/wiki/ISO_4217#Active_codes">ISO
- * 4217</a>.
+ * 4217</a>
  *
- * <p>Example: {@code CAD} for Canadian dollars, {@code EUR} for euros or {@code JPY} for Japanese
- * yen.
- *
- * <p>Severity: {@code SeverityLevel.ERROR}
+ * <p>Example: `CAD` for Canadian dollars, `EUR` for euros or `JPY` for Japanese yen.
  */
 @GtfsValidationNotice(severity = ERROR, sections = @SectionRefs(FILED_TYPES))
 public class InvalidCurrencyNotice extends ValidationNotice {

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidDateNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidDateNotice.java
@@ -26,9 +26,7 @@
  *
  * <p>Dates must have the YYYYMMDD format.
  *
- * <p>Example: {@code 20180913} for September 13th, 2018.
- *
- * <p>Severity: {@code SeverityLevel.ERROR}
+ * <p>Example: `20180913` for September 13th, 2018.
  */
 @GtfsValidationNotice(severity = ERROR, sections = @SectionRefs(FILED_TYPES))
 public class InvalidDateNotice extends ValidationNotice {

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidEmailNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidEmailNotice.java
@@ -25,11 +25,8 @@
 /**
  * A field contains a malformed email address.
  *
- * <p>Definitions for valid emails are quite vague. We perform strict validation in the upstream
- * using the Apache Commons EmailValidator.
- *
- * <p><a href="https://github.com/google/transit/blob/master/gtfs/spec/en/reference.md">GTFS
- * reference</a> does not provide any special requirements or standards.
+ * <p>Definitions for valid emails are quite vague. We perform strict validation using the Apache
+ * Commons EmailValidator.
  */
 @GtfsValidationNotice(
     severity = ERROR,

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidFloatNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidFloatNotice.java
@@ -21,11 +21,7 @@
 import org.mobilitydata.gtfsvalidator.annotation.GtfsValidationNotice;
 import org.mobilitydata.gtfsvalidator.annotation.GtfsValidationNotice.SectionRefs;
 
-/**
- * A field cannot be parsed as a floating point number.
- *
- * <p>Severity: {@code SeverityLevel.ERROR}
- */
+/** A field cannot be parsed as a floating point number. */
 @GtfsValidationNotice(severity = ERROR, sections = @SectionRefs(FILED_TYPES))
 public class InvalidFloatNotice extends ValidationNotice {
 

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidIntegerNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidIntegerNotice.java
@@ -21,11 +21,7 @@
 import org.mobilitydata.gtfsvalidator.annotation.GtfsValidationNotice;
 import org.mobilitydata.gtfsvalidator.annotation.GtfsValidationNotice.SectionRefs;
 
-/**
- * A field cannot be parsed as an integer.
- *
- * <p>Severity: {@code SeverityLevel.ERROR}
- */
+/** A field cannot be parsed as an integer. */
 @GtfsValidationNotice(severity = ERROR, sections = @SectionRefs(FILED_TYPES))
 public class InvalidIntegerNotice extends ValidationNotice {
 

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidLanguageCodeNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidLanguageCodeNotice.java
@@ -27,9 +27,7 @@
  * <p>Language codes must follow <a href="http://www.rfc-editor.org/rfc/bcp/bcp47.txt">IETF BCP
  * 47</a>.
  *
- * <p>Example: {@code en} for English, {@code en-US} for American English or {@code de} for German.
- *
- * <p>Severity: {@code SeverityLevel.ERROR}
+ * <p>Example: `en` for English, `en-US` for American English or `de` for German.
  */
 @GtfsValidationNotice(severity = ERROR, sections = @SectionRefs(FILED_TYPES))
 public class InvalidLanguageCodeNotice extends ValidationNotice {

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidPhoneNumberNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidPhoneNumberNotice.java
@@ -24,11 +24,10 @@
 /**
  * A field contains a malformed phone number.
  *
- * <p>Definitions for valid phone numbers are quite vague. We perform strict validation in the
- * upstream using the Google libphonenumber.
- *
- * <p><a href="https://github.com/google/transit/blob/master/gtfs/spec/en/reference.md">GTFS
- * reference</a> does not provide any special requirements or standards.
+ * <p>This rule uses the
+ * [PhoneNumberUtil](https://www.javadoc.io/doc/com.googlecode.libphonenumber/libphonenumber/8.4.1/com/google/i18n/phonenumbers/PhoneNumberUtil.html)
+ * class to validate a phone number based on a country code. If no country code is provided in the
+ * parameters used to run the validator, this notice won't be emitted.
  */
 @GtfsValidationNotice(severity = ERROR, sections = @SectionRefs(FILED_TYPES))
 public class InvalidPhoneNumberNotice extends ValidationNotice {

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidRowLengthNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidRowLengthNotice.java
@@ -23,9 +23,9 @@
 import org.mobilitydata.gtfsvalidator.annotation.GtfsValidationNotice.UrlRef;
 
 /**
- * A row in the input file has a different number of values than specified by the CSV header.
+ * Invalid csv row length.
  *
- * <p>Severity: {@code SeverityLevel.ERROR}
+ * <p>A row in the input file has a different number of values than specified by the CSV header.
  */
 @GtfsValidationNotice(
     severity = ERROR,

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidTimeNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidTimeNotice.java
@@ -24,11 +24,9 @@
 /**
  * A field cannot be parsed as time.
  *
- * <p>Time must be in the {@code H:MM:SS}, {@code HH:MM:SS} or {@code HHH:MM:SS} format.
+ * <p>Time must be in the `H:MM:SS`, `HH:MM:SS` or `HHH:MM:SS` format.
  *
- * <p>Example: {@code 14:30:00} for 2:30PM or {@code 25:35:00} for 1:35AM on the next day.
- *
- * <p>Severity: {@code SeverityLevel.ERROR}
+ * <p>Example: `14:30:00` for 2:30PM or `25:35:00` for 1:35AM on the next day.
  */
 @GtfsValidationNotice(severity = ERROR, sections = @SectionRefs(FILED_TYPES))
 public class InvalidTimeNotice extends ValidationNotice {

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidTimezoneNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidTimezoneNotice.java
@@ -28,9 +28,7 @@
  * names never contain the space character but may contain an underscore. Refer to <a
  * href="http://en.wikipedia.org/wiki/List_of_tz_zones">Wikipedia</a> for a list of valid values.
  *
- * <p>Example: {@code Asia/Tokyo}, {@code America/Los_Angeles} or {@code Africa/Cairo}.
- *
- * <p>Severity: {@code SeverityLevel.ERROR}
+ * <p>Example: `Asia/Tokyo`, `America/Los_Angeles` or `Africa/Cairo`.
  */
 @GtfsValidationNotice(severity = ERROR, sections = @SectionRefs(FILED_TYPES))
 public class InvalidTimezoneNotice extends ValidationNotice {

diff --git a/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidUrlNotice.java b/core/src/main/java/org/mobilitydata/gtfsvalidator/notice/InvalidUrlNotice.java
@@ -25,19 +25,8 @@
 /**
  * A field contains a malformed URL.
  *
- * <p>Definitions for valid URLs are quite vague. We perform strict validation in the upstream using
- * the Apache Common UrlValidator.
- *
- * <p><a href="https://github.com/google/transit/blob/master/gtfs/spec/en/reference.md">GTFS
- * reference</a> describes the requirements in the following way.
- *
- * <p><i>A fully qualified URL that includes http:// or https://, and any special characters in the
- * URL must be correctly escaped. See the following <a
- * href="http://www.w3.org/Addressing/URL/4_URI_Recommentations.html">URI recommentations</a> for a
- * description of how to create fully qualified URL values.</i>
- *
- * <p>However, some production feeds may use certain characters without escaping and those URL may
- * be still openable in modern browsers.
+ * <p>Definitions for valid URLs are quite vague. We perform strict validation using the Apache
+ * Commons UrlValidator.
  */
 @GtfsValidationNotice(
     severity = ERROR,