stash/pkg/scraper/query_url.go

104 lines
2.3 KiB
Go
Raw Permalink Normal View History

2020-10-22 00:56:04 +00:00
package scraper
import (
"path/filepath"
"strings"
"github.com/stashapp/stash/pkg/models"
)
type queryURLReplacements map[string]mappedRegexConfigs
type queryURLParameters map[string]string
func queryURLParametersFromScene(scene *models.Scene) queryURLParameters {
ret := make(queryURLParameters)
ret["checksum"] = scene.Checksum
ret["oshash"] = scene.OSHash
ret["filename"] = filepath.Base(scene.Path)
File storage rewrite (#2676) * Restructure data layer part 2 (#2599) * Refactor and separate image model * Refactor image query builder * Handle relationships in image query builder * Remove relationship management methods * Refactor gallery model/query builder * Add scenes to gallery model * Convert scene model * Refactor scene models * Remove unused methods * Add unit tests for gallery * Add image tests * Add scene tests * Convert unnecessary scene value pointers to values * Convert unnecessary pointer values to values * Refactor scene partial * Add scene partial tests * Refactor ImagePartial * Add image partial tests * Refactor gallery partial update * Add partial gallery update tests * Use zero/null package for null values * Add files and scan system * Add sqlite implementation for files/folders * Add unit tests for files/folders * Image refactors * Update image data layer * Refactor gallery model and creation * Refactor scene model * Refactor scenes * Don't set title from filename * Allow galleries to freely add/remove images * Add multiple scene file support to graphql and UI * Add multiple file support for images in graphql/UI * Add multiple file for galleries in graphql/UI * Remove use of some deprecated fields * Remove scene path usage * Remove gallery path usage * Remove path from image * Move funscript to video file * Refactor caption detection * Migrate existing data * Add post commit/rollback hook system * Lint. Comment out import/export tests * Add WithDatabase read only wrapper * Prepend tasks to list * Add 32 pre-migration * Add warnings in release and migration notes
2022-07-13 06:30:54 +00:00
if scene.Title != "" {
ret["title"] = scene.Title
}
if len(scene.URLs.List()) > 0 {
ret["url"] = scene.URLs.List()[0]
File storage rewrite (#2676) * Restructure data layer part 2 (#2599) * Refactor and separate image model * Refactor image query builder * Handle relationships in image query builder * Remove relationship management methods * Refactor gallery model/query builder * Add scenes to gallery model * Convert scene model * Refactor scene models * Remove unused methods * Add unit tests for gallery * Add image tests * Add scene tests * Convert unnecessary scene value pointers to values * Convert unnecessary pointer values to values * Refactor scene partial * Add scene partial tests * Refactor ImagePartial * Add image partial tests * Refactor gallery partial update * Add partial gallery update tests * Use zero/null package for null values * Add files and scan system * Add sqlite implementation for files/folders * Add unit tests for files/folders * Image refactors * Update image data layer * Refactor gallery model and creation * Refactor scene model * Refactor scenes * Don't set title from filename * Allow galleries to freely add/remove images * Add multiple scene file support to graphql and UI * Add multiple file support for images in graphql/UI * Add multiple file for galleries in graphql/UI * Remove use of some deprecated fields * Remove scene path usage * Remove gallery path usage * Remove path from image * Move funscript to video file * Refactor caption detection * Migrate existing data * Add post commit/rollback hook system * Lint. Comment out import/export tests * Add WithDatabase read only wrapper * Prepend tasks to list * Add 32 pre-migration * Add warnings in release and migration notes
2022-07-13 06:30:54 +00:00
}
return ret
}
func queryURLParametersFromScrapedScene(scene ScrapedSceneInput) queryURLParameters {
ret := make(queryURLParameters)
setField := func(field string, value *string) {
if value != nil {
ret[field] = *value
}
}
setField("title", scene.Title)
setField("code", scene.Code)
if len(scene.URLs) > 0 {
setField("url", &scene.URLs[0])
} else {
setField("url", scene.URL)
}
setField("date", scene.Date)
setField("details", scene.Details)
setField("director", scene.Director)
setField("remote_site_id", scene.RemoteSiteID)
return ret
}
func queryURLParameterFromURL(url string) queryURLParameters {
ret := make(queryURLParameters)
ret["url"] = url
2020-10-22 00:56:04 +00:00
return ret
}
func queryURLParametersFromGallery(gallery *models.Gallery) queryURLParameters {
ret := make(queryURLParameters)
ret["checksum"] = gallery.PrimaryChecksum()
File storage rewrite (#2676) * Restructure data layer part 2 (#2599) * Refactor and separate image model * Refactor image query builder * Handle relationships in image query builder * Remove relationship management methods * Refactor gallery model/query builder * Add scenes to gallery model * Convert scene model * Refactor scene models * Remove unused methods * Add unit tests for gallery * Add image tests * Add scene tests * Convert unnecessary scene value pointers to values * Convert unnecessary pointer values to values * Refactor scene partial * Add scene partial tests * Refactor ImagePartial * Add image partial tests * Refactor gallery partial update * Add partial gallery update tests * Use zero/null package for null values * Add files and scan system * Add sqlite implementation for files/folders * Add unit tests for files/folders * Image refactors * Update image data layer * Refactor gallery model and creation * Refactor scene model * Refactor scenes * Don't set title from filename * Allow galleries to freely add/remove images * Add multiple scene file support to graphql and UI * Add multiple file support for images in graphql/UI * Add multiple file for galleries in graphql/UI * Remove use of some deprecated fields * Remove scene path usage * Remove gallery path usage * Remove path from image * Move funscript to video file * Refactor caption detection * Migrate existing data * Add post commit/rollback hook system * Lint. Comment out import/export tests * Add WithDatabase read only wrapper * Prepend tasks to list * Add 32 pre-migration * Add warnings in release and migration notes
2022-07-13 06:30:54 +00:00
if gallery.Path != "" {
ret["filename"] = filepath.Base(gallery.Path)
File storage rewrite (#2676) * Restructure data layer part 2 (#2599) * Refactor and separate image model * Refactor image query builder * Handle relationships in image query builder * Remove relationship management methods * Refactor gallery model/query builder * Add scenes to gallery model * Convert scene model * Refactor scene models * Remove unused methods * Add unit tests for gallery * Add image tests * Add scene tests * Convert unnecessary scene value pointers to values * Convert unnecessary pointer values to values * Refactor scene partial * Add scene partial tests * Refactor ImagePartial * Add image partial tests * Refactor gallery partial update * Add partial gallery update tests * Use zero/null package for null values * Add files and scan system * Add sqlite implementation for files/folders * Add unit tests for files/folders * Image refactors * Update image data layer * Refactor gallery model and creation * Refactor scene model * Refactor scenes * Don't set title from filename * Allow galleries to freely add/remove images * Add multiple scene file support to graphql and UI * Add multiple file support for images in graphql/UI * Add multiple file for galleries in graphql/UI * Remove use of some deprecated fields * Remove scene path usage * Remove gallery path usage * Remove path from image * Move funscript to video file * Refactor caption detection * Migrate existing data * Add post commit/rollback hook system * Lint. Comment out import/export tests * Add WithDatabase read only wrapper * Prepend tasks to list * Add 32 pre-migration * Add warnings in release and migration notes
2022-07-13 06:30:54 +00:00
}
if gallery.Title != "" {
ret["title"] = gallery.Title
}
2020-10-22 00:56:04 +00:00
if len(gallery.URLs.List()) > 0 {
ret["url"] = gallery.URLs.List()[0]
2020-10-22 00:56:04 +00:00
}
return ret
}
func (p queryURLParameters) applyReplacements(r queryURLReplacements) {
for k, v := range p {
rpl, found := r[k]
if found {
p[k] = rpl.apply(v)
}
}
}
func (p queryURLParameters) constructURL(url string) string {
ret := url
for k, v := range p {
Enable gocritic (#1848) * Don't capitalize local variables ValidCodecs -> validCodecs * Capitalize deprecation markers A deprecated marker should be capitalized. * Use re.MustCompile for static regexes If the regex fails to compile, it's a programmer error, and should be treated as such. The regex is entirely static. * Simplify else-if constructions Rewrite else { if cond {}} to else if cond {} * Use a switch statement to analyze formats Break an if-else chain. While here, simplify code flow. Also introduce a proper static error for unsupported image formats, paving the way for being able to check against the error. * Rewrite ifElse chains into switch statements The "Effective Go" https://golang.org/doc/effective_go#switch document mentions it is more idiomatic to write if-else chains as switches when it is possible. Find all the plain rewrite occurrences in the code base and rewrite. In some cases, the if-else chains are replaced by a switch scrutinizer. That is, the code sequence if x == 1 { .. } else if x == 2 { .. } else if x == 3 { ... } can be rewritten into switch x { case 1: .. case 2: .. case 3: .. } which is clearer for the compiler: it can decide if the switch is better served by a jump-table then a branch-chain. * Rewrite switches, introduce static errors Introduce two new static errors: * `ErrNotImplmented` * `ErrNotSupported` And use these rather than forming new generative errors whenever the code is called. Code can now test on the errors (since they are static and the pointers to them wont change). Also rewrite ifElse chains into switches in this part of the code base. * Introduce a StashBoxError in configuration Since all stashbox errors are the same, treat them as such in the code base. While here, rewrite an ifElse chain. In the future, it might be beneifical to refactor configuration errors into one error which can handle missing fields, which context the error occurs in and so on. But for now, try to get an overview of the error categories by hoisting them into static errors. * Get rid of an else-block in transaction handling If we succesfully `recover()`, we then always `panic()`. This means the rest of the code is not reachable, so we can avoid having an else-block here. It also solves an ifElse-chain style check in the code base. * Use strings.ReplaceAll Rewrite strings.Replace(s, o, n, -1) into strings.ReplaceAll(s, o, n) To make it consistent and clear that we are doing an all-replace in the string rather than replacing parts of it. It's more of a nitpick since there are no implementation differences: the stdlib implementation is just to supply -1. * Rewrite via gocritic's assignOp Statements of the form x = x + e is rewritten into x += e where applicable. * Formatting * Review comments handled Stash-box is a proper noun. Rewrite a switch into an if-chain which returns on the first error encountered. * Use context.TODO() over context.Background() Patch in the same vein as everything else: use the TODO() marker so we can search for it later and link it into the context tree/tentacle once it reaches down to this level in the code base. * Tell the linter to ignore a section in manager_tasks.go The section is less readable, so mark it with a nolint for now. Because the rewrite enables a ifElseChain, also mark that as nolint for now. * Use strings.ReplaceAll over strings.Replace * Apply an ifElse rewrite else { if .. { .. } } rewrite into else if { .. } * Use switch-statements over ifElseChains Rewrite chains of if-else into switch statements. Where applicable, add an early nil-guard to simplify case analysis. Also, in ScanTask's Start(..), invert the logic to outdent the whole block, and help the reader: if it's not a scene, the function flow is now far more local to the top of the function, and it's clear that the rest of the function has to do with scene management. * Enable gocritic on the code base. Disable appendAssign for now since we aren't passing that check yet. * Document the nolint additions * Document StashBoxBatchPerformerTagInput
2021-10-18 03:12:40 +00:00
ret = strings.ReplaceAll(ret, "{"+k+"}", v)
2020-10-22 00:56:04 +00:00
}
return ret
}
// replaceURL does a partial URL Replace ( only url parameter is used)
func replaceURL(url string, scraperConfig scraperTypeConfig) string {
u := url
queryURL := queryURLParameterFromURL(u)
if scraperConfig.QueryURLReplacements != nil {
queryURL.applyReplacements(scraperConfig.QueryURLReplacements)
u = queryURL.constructURL(scraperConfig.QueryURL)
}
return u
}