From abf8aa05d39688a69afd6c389ab517263982572e Mon Sep 17 00:00:00 2001
From: ines <ines@ines.io>
Date: Mon, 30 Oct 2017 18:39:38 +0100
Subject: [PATCH] Populate --create-meta defaults from file if available

If meta.json is found in directory and user chooses to overwrite it, show existing data as defaults.
---
 spacy/cli/package.py             | 40 +++++++++++++++++---------------
 website/api/_top-level/_cli.jade | 18 +++++++-------
 2 files changed, 31 insertions(+), 27 deletions(-)

diff --git a/spacy/cli/package.py b/spacy/cli/package.py
index d1984fe65..3157ba99d 100644
--- a/spacy/cli/package.py
+++ b/spacy/cli/package.py
@@ -16,10 +16,11 @@ from .. import about
     input_dir=("directory with model data", "positional", None, str),
     output_dir=("output parent directory", "positional", None, str),
     meta_path=("path to meta.json", "option", "m", str),
-    create_meta=("create meta.json, even if one exists in directory", "flag",
-                 "c", bool),
-    force=("force overwriting of existing folder in output directory", "flag",
-           "f", bool))
+    create_meta=("create meta.json, even if one exists in directory – if "
+                 "existing meta is found, entries are shown as defaults in "
+                 "the command line prompt", "flag", "c", bool),
+    force=("force overwriting of existing model directory in output directory",
+           "flag", "f", bool))
 def package(cmd, input_dir, output_dir, meta_path=None, create_meta=False,
             force=False):
     """
@@ -41,13 +42,13 @@ def package(cmd, input_dir, output_dir, meta_path=None, create_meta=False,
     template_manifest = get_template('MANIFEST.in')
     template_init = get_template('xx_model_name/__init__.py')
     meta_path = meta_path or input_path / 'meta.json'
-    if not create_meta and meta_path.is_file():
-        prints(meta_path, title="Reading meta.json from file")
+    if meta_path.is_file():
         meta = util.read_json(meta_path)
-    else:
-        meta = generate_meta(input_dir)
+        if not create_meta:  # only print this if user doesn't want to overwrite
+            prints(meta_path, title="Loaded meta.json from file")
+        else:
+            meta = generate_meta(input_dir, meta)
     meta = validate_meta(meta, ['lang', 'name', 'version'])
-
     model_name = meta['lang'] + '_' + meta['name']
     model_name_v = model_name + '-' + meta['version']
     main_path = output_path / model_name_v
@@ -82,18 +83,19 @@ def create_file(file_path, contents):
     file_path.open('w', encoding='utf-8').write(contents)
 
 
-def generate_meta(model_path):
-    meta = {}
-    settings = [('lang', 'Model language', 'en'),
-                ('name', 'Model name', 'model'),
-                ('version', 'Model version', '0.0.0'),
+def generate_meta(model_path, existing_meta):
+    meta = existing_meta or {}
+    settings = [('lang', 'Model language', meta.get('lang', 'en')),
+                ('name', 'Model name', meta.get('name', 'model')),
+                ('version', 'Model version', meta.get('version', '0.0.0')),
                 ('spacy_version', 'Required spaCy version',
                  '>=%s,<3.0.0' % about.__version__),
-                ('description', 'Model description', False),
-                ('author', 'Author', False),
-                ('email', 'Author email', False),
-                ('url', 'Author website', False),
-                ('license', 'License', 'CC BY-NC 3.0')]
+                ('description', 'Model description',
+                  meta.get('description', False)),
+                ('author', 'Author', meta.get('author', False)),
+                ('email', 'Author email', meta.get('email', False)),
+                ('url', 'Author website', meta.get('url', False)),
+                ('license', 'License', meta.get('license', 'CC BY-SA 3.0'))]
     nlp = util.load_model_from_path(Path(model_path))
     meta['pipeline'] = nlp.pipe_names
     meta['vectors'] = {'width': nlp.vocab.vectors_length,
diff --git a/website/api/_top-level/_cli.jade b/website/api/_top-level/_cli.jade
index f19eb43d0..aa13abc12 100644
--- a/website/api/_top-level/_cli.jade
+++ b/website/api/_top-level/_cli.jade
@@ -453,10 +453,11 @@ p
 p
     |  Generate a #[+a("/usage/training#models-generating") model Python package]
     |  from an existing model data directory. All data files are copied over.
-    |  If the path to a meta.json is supplied, or a meta.json is found in the
-    |  input directory, this file is used. Otherwise, the data can be entered
-    |  directly from the command line. The required file templates are downloaded
-    |  from #[+src(gh("spacy-dev-resources", "templates/model")) GitHub] to make
+    |  If the path to a #[code meta.json] is supplied, or a #[code meta.json] is
+    |  found in the input directory, this file is used. Otherwise, the data can
+    |  be entered directly from the command line. The required file templates
+    |  are downloaded from
+    |  #[+src(gh("spacy-dev-resources", "templates/model")) GitHub] to make
     |  sure you're always using the latest versions. This means you need to be
     |  connected to the internet to use this command.
 
@@ -477,15 +478,16 @@ p
     +row
         +cell #[code --meta-path], #[code -m]
         +cell option
-        +cell #[+tag-new(2)] Path to meta.json file (optional).
+        +cell #[+tag-new(2)] Path to #[code meta.json] file (optional).
 
     +row
         +cell #[code --create-meta], #[code -c]
         +cell flag
         +cell
-            |  #[+tag-new(2)] Create a meta.json file on the command line, even
-            |  if one already exists in the directory.
-
+            |  #[+tag-new(2)] Create a #[code meta.json] file on the command
+            |  line, even if one already exists in the directory. If an
+            |  existing file is found, its entries will be shown as the defaults
+            |  in the command line prompt.
     +row
         +cell #[code --force], #[code -f]
         +cell flag