Remove scientific notation parsing.

This behaviour comes from the initial pdf.js commit but is wrong and
doesn't match other PDF readers like muPDF or pdfium.

From PDF Spec 7.3.3:

A PDF writer shall not use the PostScript language syntax for numbers with non-decimal radices (such
as 16#FFFE) or in exponential format (such as 6.02E23).

src/core/parser.js

@@ -908,7 +908,6 @@ class Lexer {
 
   getNumber() {
     let ch = this.currentChar;
-    let eNotation = false;
     let divideBy = 0; // Different from 0 if it's a floating point value.
     let sign = 1;
 
@@ -951,22 +950,15 @@ class Lexer {
     }
 
     let baseValue = ch - 0x30; // '0'
-    let powerValue = 0;
-    let powerValueSign = 1;
 
     while ((ch = this.nextChar()) >= 0) {
       if (ch >= /* '0' = */ 0x30 && ch <= /* '9' = */ 0x39) {
         const currentDigit = ch - 0x30; // '0'
-        if (eNotation) {
+        if (divideBy !== 0) {
-          // We are after an 'e' or 'E'.
+          // We are after a point.
-          powerValue = powerValue * 10 + currentDigit;
+          divideBy *= 10;
-        } else {
-          if (divideBy !== 0) {
-            // We are after a point.
-            divideBy *= 10;
-          }
-          baseValue = baseValue * 10 + currentDigit;
         }
+        baseValue = baseValue * 10 + currentDigit;
       } else if (ch === /* '.' = */ 0x2e) {
         if (divideBy === 0) {
           divideBy = 1;
@@ -978,18 +970,6 @@ class Lexer {
         // Ignore minus signs in the middle of numbers to match
         // Adobe's behavior.
         warn("Badly formatted number: minus sign in the middle");
-      } else if (ch === /* 'E' = */ 0x45 || ch === /* 'e' = */ 0x65) {
-        // 'E' can be either a scientific notation or the beginning of a new
-        // operator.
-        ch = this.peekChar();
-        if (ch === /* '+' = */ 0x2b || ch === /* '-' = */ 0x2d) {
-          powerValueSign = ch === 0x2d ? -1 : 1;
-          this.nextChar(); // Consume the sign character.
-        } else if (ch < /* '0' = */ 0x30 || ch > /* '9' = */ 0x39) {
-          // The 'E' must be the beginning of a new operator.
-          break;
-        }
-        eNotation = true;
       } else {
         // The last character doesn't belong to us.
         break;
@@ -999,9 +979,6 @@ class Lexer {
     if (divideBy !== 0) {
       baseValue /= divideBy;
     }
-    if (eNotation) {
-      baseValue *= 10 ** (powerValueSign * powerValue);
-    }
     return sign * baseValue;
   }
 

test/pdfs/.gitignore

@@ -874,3 +874,4 @@
 !bug2013793.pdf
 !bug2014080.pdf
 !two_pages.pdf
+!sci-notation.pdf

test/pdfs/sci-notation.pdf

@@ -0,0 +1,33 @@
+%PDF-1.0
+1 0 obj
+<< /Type /Catalog /Pages 2 0 R >>
+endobj
+2 0 obj
+<< /Type /Pages /Kids [3 0 R] /Count 1 >>
+endobj
+3 0 obj
+<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >>
+endobj
+4 0 obj
+<< /Length 106 >>
+stream
+BT /F1 24 Tf 50 500 Td (This line uses normal syntax) Tj ETBT /F1 1e2 Tf 50 600 Td (Hello from 1e2) Tj ET
+
+endstream
+endobj
+5 0 obj
+<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>
+endobj
+xref
+0 6
+0000000000 65535 f 
+0000000009 00000 n 
+0000000058 00000 n 
+0000000115 00000 n 
+0000000241 00000 n 
+0000000398 00000 n 
+trailer
+<< /Size 6 /Root 1 0 R >>
+startxref
+468
+%%EOF

test/test_manifest.json

@@ -13964,5 +13964,12 @@
     "firstPage": 171,
     "lastPage": 171,
     "type": "eq"
+  },
+  {
+    "id": "sci-notation",
+    "file": "pdfs/sci-notation.pdf",
+    "md5": "ead167e0328f1a1f4f8901cee501a9c4",
+    "rounds": 1,
+    "type": "eq"
   }
 ]

test/unit/parser_spec.js

@@ -94,13 +94,11 @@ describe("parser", function () {
         expect(lexer.getNumber()).toEqual(11.234);
       });
 
-      it("should parse PostScript numbers", function () {
+      it("should parse PDF numbers", function () {
         const numbers = [
           "-.002",
           "34.5",
           "-3.62",
-          "123.6e10",
-          "1E-5",
           "-1.",
           "0.0",
           "123",