Changes to comply with MyCapytain 2.0.8 (#126)

* Changes to comply with MyCapytain 2.0.8
With unit test updates
* Updated CHANGES.md and bumped version number

CHANGES.txt

@@ -1,3 +1,8 @@
+## 1.1.9 - 2018-06-26
+
+    - Added tests for new EmptyRefsDecl exception
+    - Edited several tests and unit tests to deal with this new exception
+
 ## 1.1.8 - 2018-06-25
 
 - Removed legacy functions

HookTest/capitains_units/cts.py

@@ -6,7 +6,7 @@
 
 import MyCapytain.common
 from MyCapytain.common.constants import Mimetypes
-from MyCapytain.errors import DuplicateReference, EmptyReference
+from MyCapytain.errors import DuplicateReference, EmptyReference, MissingRefsDecl
 from MyCapytain.resources.collections.cts import XmlCtsTextgroupMetadata, XmlCtsWorkMetadata
 from MyCapytain.resources.texts.local.capitains.cts import CapitainsCtsText
 
@@ -339,6 +339,7 @@ def __init__(self, path, countwords=False, timeout=30, *args, **kwargs):
         self.duplicates = list()
         self.forbiddens = list()
         self.empties = list()
+        self.capitains_errors = list()
         self.test_status = defaultdict(bool)
         self.lang = ''
         self.dtd_errors = list()
@@ -353,7 +354,13 @@ def parsable(self):
             super(CTSText_TestUnit, self).parsable()
         )
         if status is True:
-            self.Text = CapitainsCtsText(resource=self.xml.getroot())
+            try:
+                self.Text = CapitainsCtsText(resource=self.xml.getroot())
+            except MissingRefsDecl as E:
+                self.Text = None
+                self.log(str(E))
+                self.capitains_errors.append(str(E))
+                yield False
         else:
             self.Text = None
         yield status

HookTest/test.py

@@ -376,6 +376,8 @@ def unit(self, filepath):
             additional["forbiddens"] = unit.forbiddens
             additional["dtd_errors"] = unit.dtd_errors
             additional['language'] = unit.lang
+            additional['empties'] = unit.empties
+            additional['capitains_errors'] = unit.capitains_errors
             if self.countwords:
                 additional["words"] = unit.count
         return self.cover(filepath, results, testtype=texttype, logs=logs, additional=additional), filepath, additional
@@ -498,6 +500,8 @@ def end(self):
             duplicate_nodes = ''
             forbidden_chars = ''
             dtd_errors = ''
+            capitains_errors = ''
+            empty_refs = ''
             num_texts = 0
             num_failed = 0
             print('', flush=True)
@@ -542,6 +546,14 @@ def end(self):
                         dtd_errors += '\t{name}\t{nodes}\n'.format(name=magenta(os.path.basename(unit.name)),
                                                                    nodes=', '.join(unit.additional["dtd_errors"]))
 
+                    if unit.additional["capitains_errors"]:
+                        capitains_errors += '\t{name}\t{nodes}\n'.format(name=magenta(os.path.basename(unit.name)),
+                                                                   nodes=', '.join(unit.additional["capitains_errors"]))
+
+                    if unit.additional["empties"]:
+                        empty_refs += '\t{name}\t{nodes}\n'.format(name=magenta(os.path.basename(unit.name)),
+                                                                   nodes=', '.join(unit.additional["empties"]))
+
                     if self.verbose >= 7 or unit.status is False:
                         if self.countwords:
                             row = [
@@ -575,12 +587,19 @@ def end(self):
                     forbidden_chars = magenta('Forbidden characters found:\n') + forbidden_chars + '\n'
                 if dtd_errors:
                     dtd_errors = magenta('DTD errors found:\n') + dtd_errors + '\n'
+                if empty_refs:
+                    empty_refs = magenta('Empty references found:\n') + empty_refs + '\n'
             else:
                 duplicate_nodes = forbidden_chars = dtd_errors = ''
 
-            print("{dupes}{forbs}{dtds}>>> End of the test !\n".format(dupes=duplicate_nodes,
-                                                                      forbs=forbidden_chars,
-                                                                      dtds=dtd_errors))
+            if capitains_errors:
+                capitains_errors = magenta('CapiTainS parsing errors found:\n') + capitains_errors + '\n'
+
+            print("{caps}{dupes}{forbs}{dtds}{empts}>>> End of the test !\n".format(caps=capitains_errors,
+                                                                                    dupes=duplicate_nodes,
+                                                                                    forbs=forbidden_chars,
+                                                                                    dtds=dtd_errors,
+                                                                                    empts=empty_refs))
             t_pass = num_texts - num_failed
             cov = round(statistics.mean([test.coverage for test in self.results.values()]), ndigits=2)
             results_table = PT(["HookTestResults", ""])

setup.py

@@ -10,7 +10,7 @@
 
 setup(
     name='HookTest',
-    version="1.1.8",
+    version="1.1.9",
     description='Hook Test Script for GitHub/CapiTainS repositories',
     long_description=long_description,
     url='http://github.com/Capitains/HookTest',

tests/repo2/data/tlg2255/perseus001/refsDecl_no_targets.xml

@@ -0,0 +1,85 @@
+<?xml version="1.0" encoding="UTF-8"?> <?xml-model href="http://www.stoa.org/epidoc/schema/latest/tei-epidoc.rng" schematypens="http://relaxng.org/ns/structure/1.0"?><TEI xmlns="http://www.tei-c.org/ns/1.0"><teiHeader><fileDesc>
+      <titleStmt>
+        <title>Encomium of Helen</title>
+        <author>Gorgias</author>
+        <editor role="editor">Friedrich Blass</editor>
+      </titleStmt>
+      <publicationStmt><publisher>Trustees of Tufts University</publisher><pubPlace>Medford, MA</pubPlace><authority>Perseus Project</authority></publicationStmt>
+      <sourceDesc>
+        <biblStruct>
+          <monogr>
+            <title>ΕΛΕΝΗΣ ΕΓΚΩΜΙΟΝ</title>
+            <author>ΓΟΡΓΙΟΥ</author>
+            <editor role="editor">Friedrich Blass</editor>
+            <imprint>
+              <publisher>Teubner</publisher>
+              <pubPlace>Leipzig</pubPlace>
+              <date>1908</date>
+            </imprint>
+          </monogr>
+        </biblStruct>
+
+        </sourceDesc>
+    </fileDesc><encodingDesc>
+      <refsDecl n="CTS">
+        <cRefPattern n="section" matchPattern="(.+)" replacementPattern="#xpath(/tei:TEI/tei:text/tei:body/tei:div[@type='edition']/tei:p/tei:div[@n='$1'])"/>
+      </refsDecl>
+
+    </encodingDesc><profileDesc>
+      <langUsage>
+	<language ident="grc">Greek</language>
+      </langUsage>
+    </profileDesc>
+
+  <revisionDesc>
+    <change who="Thibault Clerice" when="2016-05-17">Changed refsDecl, added seg element for capitains scheme, added del to reflect [spurious text]</change>
+  </revisionDesc>
+</teiHeader>
+
+  <text><body> <div type="edition" n="urn:cts:greekLit:tlg2255.perseus001.perseus-grc1" xml:lang="grc">
+<pb ed="alt" n="p. 91 R."/> <head>ΓΟΡΓΙΟΥ ΕΛΕΝΗΣ ΕΓΚΩΜΙΟΝ.</head>
+<p><seg n="1"><milestone unit="section" n="1"/> Κόσμος πόλει μὲν εὐανδρία, σώματι δὲ κάλλος,
+<pb ed="alt" n="679"/> ψυχῇ δὲ σοφία, πράγματι δὲ ἀρετή, λόγῳ δὲ ἀλήθεια·
+
+<pb xml:id="v.3.p.151"/>
+
+τὰ δ᾿ ἐναντία τούτων ἀκοσμία. ἄνδρα δὲ καὶ γυναῖκα
+καὶ λόγον καὶ ἔργον καὶ πόλιν καὶ πρᾶγμα χρὴ τὸ μὲν
+<pb ed="alt" n="680"/> ἄξιον ἐπαίνου ἐπαίνῳ τιμᾶν, τῷ δὲ ἀναξίῳ μῶμον 
+ἐπιτιθέναι· ἴση γὰρ ἁμαρτία καὶ ἀμαθία μέμφεσθαί τε
+τὰ ἐπαινετὰ καὶ ἐπαινεῖν τὰ μωμητά.</seg> <milestone unit="section" n="2"/><seg n="2">τοῦ δ᾿ αὐτοῦ 
+ἀνδρὸς λέξαι τε τὸ δέον ὀρθῶς καὶ ἐλέγξαι . . . . . .
+
+<add>ἐλέγξαι</add> τοὺς μεμφομένους Ἑλένην, γυναῖκα περὶ ἧς
+ὁμόφωνος καὶ ὁμόψηφος γέγονεν ἥ τε τῶν ποιητῶν
+. . . . <add>ἥ τε τῶν</add> ἀκουσάντων πίστις, ἥ τε τοῦ ὀνόματος
+φήμη τῶν συμφορῶν μνήμη γέγονεν. ἐγὼ δὲ βούλομαι
+λογισμόν τινα τῷ λόγῳ δοὺς τὴν μὲν κακῶς
+ἀκούουσαν παῦσαι τῆς αἰτίας, τοὺς δὲ μεμφομένους
+ψευδομένους ἐπιδείξας καὶ δείξας τἀληθὲς παῦσαι τῆς
+ἀμαθίας.</seg></p>
+<p><milestone unit="section" n="3"/><seg n="3">Ὅτι μὲν οὖν φύσει καὶ γένει τὰ πρῶτα τῶν πρώτων 
+ἀνδρῶν καὶ γυναικῶν ἡ γυνὴ περὶ ἧς ὅδε ὁ λόγος,
+<pb xml:id="v.3.p.152"/>
+
+οὐκ ἄδηλον οὐδ᾿ ὀλίγοις. δῆλον γὰρ ὡς μητρὸς μὲν
+Λήδας, πατρὸς δὲ τοῦ μὲν γενομένου θεοῦ, λεγομένου
+δὲ θνητοῦ, Τυνδάρεω καὶ Διός, ὧν ὁ μὲν διὰ τὸ εἶναι
+ἔδοξεν, ὁ δὲ διὰ τὸ φάναι ἐλέχθη, καὶ ἦν ὁ μὲν
+ ἀνδρῶν κράτιστος, ὁ δὲ πάντων τύραννος.</seg> <milestone unit="section" n="4"/><seg n="4">ἐκ τοιούτων
+δὲ γενομένη ἔσχε τὸ ἰσόθεον κάλλος, ὃ λαβοῦσα
+[καὶ] οὐ λαθοῦσα ἔσχε, πλείστας δὲ πλείστοις ἐπιθυμίας
+ἔρωτος ἐνειργάσατο, ἑνὶ δὲ σώματι πολλὰ σώματα
+συνήγαγεν ἀνδρῶν ἐπὶ μεγάλοις μεγάλα φρονούντων,
+ὧν οἱ μὲν πλούτου μεγέθη, οἱ δὲ εὐγενείας παλαιᾶς
+εὐδοξίαν, οἱ δὲ ἀλκῆς οἰκείας εὐεξίαν, οἱ δὲ σοφίας
+ἐπικτήτου δύναμιν ἔσχον, καὶ ἧκον ἅπαντες ὑπ᾿ ἔρωτός
+ τε φιλονίκου φιλοτιμίας τε ἀνικήτου. </seg><milestone unit="section" n="5"/><seg n="5">ὅστις μὲν
+οὖν καὶ δι᾿ ὅ τι καὶ ὅπως ἀπέπλησε τὸν ἔρωτα τὴν
+Ἑλένην λαβών, οὐ λέξω· τὸ γὰρ τοῖς εἰδόσιν ἃ ἴσασι
+λέγειν πίστιν μὲν ἔχει, τέρψιν δὲ οὐ φέρει. τὸν χρόνον
+δὲ τῷ λόγῳ τὸν τότε <add>τῷ</add> νῦν ὑπερβὰς ἐπὶ τὴν
+ἀρχὴν τοῦ μέλλοντος λόγου προβήσομαι, καὶ προθήσομαι
+τὰς αἰτίας δι᾿ ἃς εἰκὸς ἦν γενέσθαι τὸν τῆς Ἑλένης
+εἰς τὴν Τροίαν στόλον.</seg></p>
+</div></body></text></TEI>

tests/repotei/data/tei/tei/tei.tei.tei.xml

@@ -23,8 +23,9 @@
         </biblStruct>
 
         </sourceDesc>
-    </fileDesc><encodingDesc>
-
+    </fileDesc><encodingDesc><refsDecl n="CTS">
+        <cRefPattern n="section" matchPattern="(.+)" replacementPattern="#xpath(/tei:TEI/tei:text/tei:body/tei:div[@type='edition']/tei:p/tei:seg[@n='$1'])"/>
+      </refsDecl>
     </encodingDesc><profileDesc>
       <langUsage>
 	<language ident="grc">Greek</language>

tests/repotei/data/tei/tei/tei.tei.weirdurn.xml

@@ -7,23 +7,9 @@
         <editor role="editor">Friedrich Blass</editor>
       </titleStmt>
       <publicationStmt><publisher>Trustees of Tufts University</publisher><pubPlace>Medford, MA</pubPlace><authority>Perseus Project</authority></publicationStmt>
-      <sourceDesc>
-        <biblStruct>
-          <monogr>
-            <title>ΕΛΕΝΗΣ ΕΓΚΩΜΙΟΝ</title>
-            <author>ΓΟΡΓΙΟΥ</author>
-            <editor role="editor">Friedrich Blass</editor>
-            <imprint>
-              <publisher>Teubner</publisher>
-              <pubPlace>Leipzig</pubPlace>
-              <date>1908</date>
-            </imprint>
-          </monogr>
-        </biblStruct>
-
-        </sourceDesc>
-    </fileDesc><encodingDesc>
-
+    </fileDesc><encodingDesc><refsDecl n="CTS">
+        <cRefPattern n="section" matchPattern="(.+)" replacementPattern="#xpath(/tei:TEI/tei:text/tei:body/tei:div[@type='edition']/tei:p/tei:seg[@n='$1'])"/>
+      </refsDecl>
     </encodingDesc><profileDesc>
       <langUsage>
 	<language ident="grc">Greek</language>

tests/test_run.py

@@ -165,20 +165,21 @@ def test_run_local_repo_errors(self):
         ####
         #
         #   /data/capitainingest/tei2/tlg4089.tlg004.1st1k-grc1.xml
-        #   Has wrong root node
+        #   Has wrong root node and a capitains_error
         #
         ####
         text = self.filter(parsed, "/data/capitainingest/tei2/tlg4089.tlg004.1st1k-grc1.xml")
         self.assertEqual(
             {'Naming conventions': False, 'RefsDecl parsing': False, 'Epidoc DTD validation': False,
-             'URN informations': False, 'File parsing': True, 'Passage level parsing': False,
+             'URN informations': False, 'File parsing': False, 'Passage level parsing': False,
              'Available in inventory': False, 'Unique nodes found by XPath': False,
              'Duplicate passages': False, 'Forbidden characters': False, 'Correct xml:lang attribute': False,
              'Empty References': False}
             ,
-            text["units"], "Everything but XML parsing should fail in TEI.2 files"
+            text["units"], "Everything should fail in TEI.2 files"
         )
         self.assertFalse(text["status"], "Wrong XML scheme should fail file")
+        self.assertEqual(text['capitains_errors'], ['No reference declaration (refsDecl) found.'])
 
         ####
         #
@@ -380,7 +381,7 @@ def test_run_tei_errors(self):
         ####
         text = self.filter(parsed, "/data/tei/tei/tei.tei.weirdurn.xml")
         self.assertIn(
-            '>>>>>> error: element "encodingDesc" incomplete [In (L27 C20)]', text["logs"],
+            '>>>>>> error: element "fileDesc" incomplete [In (L10 C16)]', text["logs"],
             "TEI RNG Error should show"
         )
         self.assertIn(