Add --dry-run to check how many bytes would be billed, but don't actually run query (#168)

Co-authored-by: Ofek Lev <ofekmeister@gmail.com>

Author: hugovk

README.md

@@ -23,36 +23,37 @@ pypinfo is a simple CLI to access [PyPI](https://pypi.org/) download statistics
 ```console
 $ pypinfo
 Usage: pypinfo [OPTIONS] [PROJECT] [FIELDS]... COMMAND [ARGS]...
-        
-    Valid fields are:
 
-    project | version | file | pyversion | percent3 | percent2 | impl | impl-version |
-  
-    openssl | date | month | year | country | installer | installer-version |
-  
-    setuptools-version | system | system-release | distro | distro-version | cpu |
+  Valid fields are:
+
+  project | version | file | pyversion | percent3 | percent2 | impl | impl-version |
+
+  openssl | date | month | year | country | installer | installer-version |
+
+  setuptools-version | system | system-release | distro | distro-version | ci | cpu |
+
+  libc | libc-version
 
-    libc | libc-version
-    
 Options:
-    -a, --auth TEXT         Path to Google credentials JSON file.
-    --run / --test          --test simply prints the query.
-    -j, --json              Print data as JSON, with keys `rows` and `query`.
-    -i, --indent INTEGER    JSON indentation level.
-    -t, --timeout INTEGER   Milliseconds. Default: 120000 (2 minutes)
-    -l, --limit INTEGER        Maximum number of query results. Default: 10
-    -d, --days INTEGER         Number of days in the past to include. Default: 30
-    -sd, --start-date TEXT  Must be negative or YYYY-MM[-DD]. Default: -31
-    -ed, --end-date TEXT    Must be negative or YYYY-MM[-DD]. Default: -1
-    -m, --month TEXT        Shortcut for -sd & -ed for a single YYYY-MM month.
-    -w, --where TEXT        WHERE conditional. Default: file.project = "project"
-    -o, --order TEXT        Field to order by. Default: download_count
-    --all                   Show downloads by all installers, not only pip.
-    -pc, --percent          Print percentages.
-    -md, --markdown         Output as Markdown.
-    -v, --verbose           Print debug messages to stderr.
-    --version               Show the version and exit.
-    -h, --help              Show this message and exit.
+  -a, --auth TEXT         Path to Google credentials JSON file.
+  --run / --test          --test simply prints the query.
+  -n, --dry-run           Don't run query but display how much data would be processed.
+  -j, --json              Print data as JSON, with keys `rows` and `query`.
+  -i, --indent INTEGER    JSON indentation level.
+  -t, --timeout INTEGER   Milliseconds. Default: 120000 (2 minutes)
+  -l, --limit INTEGER     Maximum number of query results. Default: 10
+  -d, --days INTEGER      Number of days in the past to include. Default: 30
+  -sd, --start-date TEXT  Must be negative or YYYY-MM[-DD]. Default: -31
+  -ed, --end-date TEXT    Must be negative or YYYY-MM[-DD]. Default: -1
+  -m, --month TEXT        Shortcut for -sd & -ed for a single YYYY-MM month.
+  -w, --where TEXT        WHERE conditional. Default: file.project = "project"
+  -o, --order TEXT        Field to order by. Default: download_count
+  --all                   Show downloads by all installers, not only pip.
+  -pc, --percent          Print percentages.
+  -md, --markdown         Output as Markdown.
+  -v, --verbose           Print debug messages to stderr.
+  --version               Show the version and exit.
+  -h, --help              Show this message and exit.
 ```
 
 pypinfo accepts 0 or more options, followed by exactly 1 project, followed by

pypinfo/cli.py

@@ -82,6 +82,7 @@
 @click.argument('fields', nargs=-1, required=False)
 @click.option('--auth', '-a', help='Path to Google credentials JSON file.')
 @click.option('--run/--test', default=True, help='--test simply prints the query.')
+@click.option('--dry-run', '-n', is_flag=True, help="Don't run query but display how much data would be processed.")
 @click.option('--json', '-j', is_flag=True, help='Print data as JSON, with keys `rows` and `query`.')
 @click.option('--indent', '-i', type=int, help='JSON indentation level.')
 @click.option('--timeout', '-t', type=int, default=120000, help='Milliseconds. Default: 120000 (2 minutes)')
@@ -104,6 +105,7 @@ def pypinfo(
     fields: list[str],
     auth: str,
     run: bool,
+    dry_run: bool,
     json: bool,
     indent: int,
     timeout: int,
@@ -167,7 +169,7 @@ def pypinfo(
 
     if run:
         with create_client(get_credentials()) as client:
-            query_job = client.query(built_query, job_config=create_config())
+            query_job = client.query(built_query, job_config=create_config(dry_run))
             query_rows = query_job.result(timeout=timeout // 1000)
             rows = parse_query_result(query_rows)
 
@@ -187,12 +189,12 @@ def pypinfo(
         estimated_cost = Decimal(TIER_COST * billing_tier) / TB * Decimal(bytes_billed)
         estimated_cost_str = str(estimated_cost.quantize(TO_CENTS, rounding=ROUND_UP))
 
-        if len(rows) == 1 and not json:
+        if len(rows) == 1 and not json and not dry_run:
             # Only headers returned
             click.echo("No data returned, check project name")
             return
 
-        if percent:
+        if percent and not dry_run:
             rows = add_percentages(rows, include_sign=not json)
 
         # Only for tables, and if more than the header row + a single data row
@@ -205,8 +207,9 @@ def pypinfo(
             click.echo(f'Data billed: {billed_amount:.2f} {billed_unit}')
             click.echo(f'Estimated cost: ${estimated_cost_str}')
 
-            click.echo()
-            click.echo(tabulate(rows, markdown))
+            if not dry_run:
+                click.echo()
+                click.echo(tabulate(rows, markdown))
         else:
             query_info = {
                 'cached': from_cache,

pypinfo/core.py

@@ -26,9 +26,12 @@
 Rows = list[list[str]]
 
 
-def create_config() -> QueryJobConfig:
+def create_config(dry_run: bool = False) -> QueryJobConfig:
     config = QueryJobConfig()
     config.use_legacy_sql = False
+    if dry_run:
+        config.dry_run = True
+        config.use_query_cache = False
     return config
 
 

tests/test_core.py

@@ -33,9 +33,19 @@ def test_create_config() -> None:
     config = core.create_config()
 
     # Assert
+    assert not config.dry_run
     assert not config.use_legacy_sql
 
 
+def test_create_config_dry_run() -> None:
+    # Act
+    config = core.create_config(dry_run=True)
+
+    # Assert
+    assert config.dry_run
+    assert not config.use_query_cache
+
+
 def test_normalize_dates_yyy_mm() -> None:
     # Arrange
     start_date = "2019-03"

tox.ini

@@ -18,7 +18,8 @@ deps =
 commands =
     coverage run --parallel-mode -m pytest -W all {posargs}
     coverage combine --append
-    coverage report -m
+    coverage report --show-missing
+    coverage html
     coverage xml
 
 [testenv:lint]