-
Notifications
You must be signed in to change notification settings - Fork 55
3. The .gitify File
To define what to export, to where and how, we're using a .gitify file formatted in YAML.
An example .gitify may look like this:
data_directory: _data/
data:
contexts:
class: modContext
primary: key
content:
type: content
exclude_keys:
- editedby
- editedon
templates:
class: modTemplate
primary: templatename
extension: .html
categories:
class: modCategory
primary: category
truncate_on_force:
- modCategoryClosure
template_variables:
class: modTemplateVar
primary: name
chunks:
class: modChunk
primary: name
extension: .html
snippets:
class: modSnippet
primary: name
extension: .php
plugins:
class: modPlugin
primary: name
extension: .phpThe .gitify file structure is real simple. There are root nodes for data_directory (the relative path where to store the files) and data. data contains an array of directories to create. These directories then specify either a type that has special processing going on (i.e. content), or a class. The primary field determines the key to use in the name of the generated files. This defaults to id, but in many cases you may want to use the name as that is more human friendly.
By default files will be created with a .yaml extension, but if you want you can override that with a extension property. This can help with certain data and syntax highlighting in IDEs.
When a certain class is not part of the core models, you can define a package as well. This will run $modx->addPackage before attempting to load the data. The path is determined by looking at a [package].core_path setting suffixed with model/, [[++core_path]]components/[package]/model/or a hardcoded package_path property. For example, you could use the following in your .gitify file to load ContentBlocks Layouts & Fields:
data:
cb_fields:
class: cbField
primary: name
package: contentblocks
cb_layouts:
class: cbLayout
primary: nameAs it'll load the package into memory, it's only required to add the package once. For clarify, it can't hurt to add it to each data entry that uses it.
A Closure is a separate table in the database that a core or third party extra may use to keep information about a hierarchy in a convenient format. These are often automatically generated when creating a new object, which can result in a error messages and other issues when using Gitify build --force.
To solve this, a new truncate_on_force option was introduced in v0.6.0 that lets you define an array of class names that need their tables truncated on a force build. Truncating the closure table(s) before a forced build ensures that the model can properly create the rows in the closure table, without throwing errors.
Here are two examples of using truncate_on_force:
data:
categories:
class: modCategory
primary: category
truncate_on_force:
- modCategoryClosure
quip_comments:
class: quipComment
package: quip
primary: [thread, id]
truncate_on_force:
- quipCommentClosureWhen an object doesn't have a single primary key, or you want to get fancy, it's possible to define a composite primary key, by setting the primary attribute to an array. For example, like this:
data:
chunks:
class: modChunk
primary: [category, name]
extension: .htmlThat would grab the category and the name as primary keys, and join them together with a dot in the file name. This is a pretty bad example, and you shouldn't really use it like this.
Setup Package Providers and Install MODX Packages via the .gitify File.
data:
packages:
modx.com:
service_url: http://rest.modx.com/extras/
packages:
- Ace
- Wayfinder
modmore.com:
service_url: https://rest.modmore.com/
username: username
api_key: .modmore.com.key
packages:
- clientConfig