The refactoring will continue until morale improves.
This commit is contained in:
parent
616effdb3c
commit
73eaa0865d
@ -13,4 +13,3 @@
|
|||||||
|
|
||||||
You should have received a copy of the GNU Affero General Public License
|
You should have received a copy of the GNU Affero General Public License
|
||||||
along with this program. If not, see <http://www.gnu.org/licenses/>.
|
along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||||
|
|
||||||
|
@ -17,7 +17,7 @@ dependencies {
|
|||||||
implementation project(':code:common:service-discovery')
|
implementation project(':code:common:service-discovery')
|
||||||
implementation project(':code:common:service-client')
|
implementation project(':code:common:service-client')
|
||||||
|
|
||||||
implementation project(':code:index:index-query')
|
implementation project(':code:features-index:index-query')
|
||||||
|
|
||||||
implementation libs.lombok
|
implementation libs.lombok
|
||||||
annotationProcessor libs.lombok
|
annotationProcessor libs.lombok
|
||||||
|
@ -15,7 +15,7 @@ dependencies {
|
|||||||
implementation project(':code:common:model')
|
implementation project(':code:common:model')
|
||||||
implementation project(':code:common:config')
|
implementation project(':code:common:config')
|
||||||
implementation project(':code:libraries:guarded-regex')
|
implementation project(':code:libraries:guarded-regex')
|
||||||
implementation project(':code:crawl:crawling-model')
|
implementation project(':code:crawl-models:crawling-model')
|
||||||
|
|
||||||
implementation libs.notnull
|
implementation libs.notnull
|
||||||
implementation libs.lombok
|
implementation libs.lombok
|
@ -17,7 +17,7 @@ dependencies {
|
|||||||
implementation project(':code:common:service-client')
|
implementation project(':code:common:service-client')
|
||||||
implementation project(':code:libraries:language-processing')
|
implementation project(':code:libraries:language-processing')
|
||||||
|
|
||||||
implementation project(':code:crawl:common')
|
implementation project(':code:crawl-models:common')
|
||||||
|
|
||||||
implementation libs.lombok
|
implementation libs.lombok
|
||||||
annotationProcessor libs.lombok
|
annotationProcessor libs.lombok
|
4
code/crawl-models/converting-model/readme.md
Normal file
4
code/crawl-models/converting-model/readme.md
Normal file
@ -0,0 +1,4 @@
|
|||||||
|
# Converting Models
|
||||||
|
|
||||||
|
Contains models shared by the [converting-process](../../crawl/converting-process/) and
|
||||||
|
[loading-process](../../crawl/loading-process/).
|
@ -1,7 +1,7 @@
|
|||||||
# Crawling Models
|
# Crawling Models
|
||||||
|
|
||||||
Contains models shared by the [crawling-process](../crawling-process/) and
|
Contains models shared by the [crawling-process](../../crawl/crawling-process/) and
|
||||||
[converting-process](../converting-process/).
|
[converting-process](../../crawl/converting-process/).
|
||||||
|
|
||||||
## Central Classes
|
## Central Classes
|
||||||
|
|
@ -1,4 +0,0 @@
|
|||||||
# Converting Models
|
|
||||||
|
|
||||||
Contains models shared by the [converting-process](../converting-process/) and
|
|
||||||
[loading-process](../loading-process/).
|
|
@ -33,13 +33,13 @@ dependencies {
|
|||||||
implementation project(':code:libraries:big-string')
|
implementation project(':code:libraries:big-string')
|
||||||
implementation project(':code:libraries:language-processing')
|
implementation project(':code:libraries:language-processing')
|
||||||
|
|
||||||
implementation project(':code:crawl:common')
|
implementation project(':code:crawl-models:common')
|
||||||
implementation project(':code:crawl:converting-model')
|
implementation project(':code:crawl-models:converting-model')
|
||||||
implementation project(':code:crawl:crawling-model')
|
implementation project(':code:crawl-models:crawling-model')
|
||||||
|
|
||||||
implementation project(':code:features:adblock')
|
implementation project(':code:features-crawl:adblock')
|
||||||
implementation project(':code:features:pubdate')
|
implementation project(':code:features-crawl:pubdate')
|
||||||
implementation project(':code:features:topic-detection')
|
implementation project(':code:features-crawl:topic-detection')
|
||||||
|
|
||||||
implementation libs.lombok
|
implementation libs.lombok
|
||||||
annotationProcessor libs.lombok
|
annotationProcessor libs.lombok
|
||||||
|
@ -21,8 +21,8 @@ tasks.distZip.enabled = false
|
|||||||
dependencies {
|
dependencies {
|
||||||
implementation project(':code:common:model')
|
implementation project(':code:common:model')
|
||||||
implementation project(':code:common:service')
|
implementation project(':code:common:service')
|
||||||
implementation project(':code:crawl:crawling-model')
|
implementation project(':code:crawl-models:crawling-model')
|
||||||
implementation project(':code:crawl:common')
|
implementation project(':code:crawl-models:common')
|
||||||
|
|
||||||
implementation libs.lombok
|
implementation libs.lombok
|
||||||
annotationProcessor libs.lombok
|
annotationProcessor libs.lombok
|
||||||
|
@ -27,9 +27,9 @@ dependencies {
|
|||||||
implementation project(':code:common:service-discovery')
|
implementation project(':code:common:service-discovery')
|
||||||
implementation project(':code:common:service-client')
|
implementation project(':code:common:service-client')
|
||||||
implementation project(':code:libraries:language-processing')
|
implementation project(':code:libraries:language-processing')
|
||||||
implementation project(':code:crawl:common')
|
implementation project(':code:crawl-models:common')
|
||||||
implementation project(':code:crawl:crawling-model')
|
implementation project(':code:crawl-models:crawling-model')
|
||||||
implementation project(':code:crawl:converting-model')
|
implementation project(':code:crawl-models:converting-model')
|
||||||
|
|
||||||
implementation libs.lombok
|
implementation libs.lombok
|
||||||
annotationProcessor libs.lombok
|
annotationProcessor libs.lombok
|
||||||
|
@ -20,11 +20,13 @@ dependencies {
|
|||||||
implementation project(':code:common:service-discovery')
|
implementation project(':code:common:service-discovery')
|
||||||
implementation project(':code:common:service-client')
|
implementation project(':code:common:service-client')
|
||||||
implementation project(':code:libraries:language-processing')
|
implementation project(':code:libraries:language-processing')
|
||||||
implementation project(':code:crawl:common')
|
|
||||||
implementation project(':code:crawl:crawling-model')
|
implementation project(':code:crawl-models:common')
|
||||||
|
implementation project(':code:crawl-models:crawling-model')
|
||||||
|
|
||||||
implementation project(':code:crawl:converting-process')
|
implementation project(':code:crawl:converting-process')
|
||||||
implementation project(':code:features:adblock')
|
implementation project(':code:features-crawl:adblock')
|
||||||
implementation project(':code:features:topic-detection')
|
implementation project(':code:features-crawl:topic-detection')
|
||||||
|
|
||||||
implementation libs.lombok
|
implementation libs.lombok
|
||||||
annotationProcessor libs.lombok
|
annotationProcessor libs.lombok
|
||||||
|
@ -24,15 +24,15 @@ dependencies {
|
|||||||
implementation project(':code:common:service')
|
implementation project(':code:common:service')
|
||||||
implementation project(':code:common:service-discovery')
|
implementation project(':code:common:service-discovery')
|
||||||
implementation project(':code:common:service-client')
|
implementation project(':code:common:service-client')
|
||||||
implementation project(':code:index:lexicon')
|
implementation project(':code:features-index:lexicon')
|
||||||
implementation project(':code:index:index-journal')
|
implementation project(':code:features-index:index-journal')
|
||||||
implementation project(':code:libraries:language-processing')
|
implementation project(':code:libraries:language-processing')
|
||||||
|
|
||||||
testImplementation project(':code:services-core:search-service')
|
testImplementation project(':code:services-core:search-service')
|
||||||
|
|
||||||
implementation project(':code:crawl:common')
|
implementation project(':code:crawl-models:common')
|
||||||
implementation project(':code:crawl:crawling-model')
|
implementation project(':code:crawl-models:crawling-model')
|
||||||
implementation project(':code:crawl:converting-model')
|
implementation project(':code:crawl-models:converting-model')
|
||||||
|
|
||||||
|
|
||||||
implementation libs.lombok
|
implementation libs.lombok
|
||||||
|
@ -8,13 +8,13 @@ based on the content in the database.
|
|||||||
## 2. Crawl Process
|
## 2. Crawl Process
|
||||||
|
|
||||||
The [crawling-process](crawling-process/) fetches website contents and saves them
|
The [crawling-process](crawling-process/) fetches website contents and saves them
|
||||||
as compressed JSON models described in [crawling-model](crawling-model/).
|
as compressed JSON models described in [crawling-model](../crawl-models/crawling-model/).
|
||||||
|
|
||||||
## 3. Converting Process
|
## 3. Converting Process
|
||||||
|
|
||||||
The [converting-process](converting-process/) reads crawl data from the crawling step and
|
The [converting-process](converting-process/) reads crawl data from the crawling step and
|
||||||
processes them, extracting keywords and metadata and saves them as compressed JSON models
|
processes them, extracting keywords and metadata and saves them as compressed JSON models
|
||||||
described in [converting-model](converting-model/).
|
described in [converting-model](../crawl-models/converting-model/).
|
||||||
|
|
||||||
## 4. Loading Process
|
## 4. Loading Process
|
||||||
|
|
||||||
|
@ -15,7 +15,7 @@ java {
|
|||||||
|
|
||||||
dependencies {
|
dependencies {
|
||||||
implementation project(':code:common:model')
|
implementation project(':code:common:model')
|
||||||
implementation project(':code:crawl:common')
|
implementation project(':code:crawl-models:common')
|
||||||
|
|
||||||
implementation libs.lombok
|
implementation libs.lombok
|
||||||
annotationProcessor libs.lombok
|
annotationProcessor libs.lombok
|
10
code/features-crawl/readme.md
Normal file
10
code/features-crawl/readme.md
Normal file
@ -0,0 +1,10 @@
|
|||||||
|
# Crawl Features
|
||||||
|
|
||||||
|
These are bits of search-engine related code that are relatively isolated pieces of business logic,
|
||||||
|
that benefit from the clarity of being kept separate from the rest of the crawling code.
|
||||||
|
|
||||||
|
|
||||||
|
* [adblock](adblock/) - Simulates Adblock
|
||||||
|
* [pubdate](pubdate/) - Determines when a document was published
|
||||||
|
* [topic-detection](topic-detection/) - Tries to identify the topic of a website
|
||||||
|
|
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue
Block a user